Upload folder using huggingface_hub
Browse files- README.md +252 -0
- config.json +64 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1171 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
README.md
ADDED
|
@@ -0,0 +1,252 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ar
|
| 4 |
+
- en
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
tags:
|
| 7 |
+
- Arabic
|
| 8 |
+
- English
|
| 9 |
+
- LLM
|
| 10 |
+
- Decoder
|
| 11 |
+
- causal-lm
|
| 12 |
+
- autoquant
|
| 13 |
+
- gptq
|
| 14 |
+
pipeline_tag: conversational
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Jais-13b-chat
|
| 18 |
+
|
| 19 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 20 |
+
|
| 21 |
+
This is a 13 billion parameter fine-tuned bilingual large language model for both Arabic and English.
|
| 22 |
+
It is based on transformer-based decoder-only (GPT-3) architecture and uses SwiGLU
|
| 23 |
+
non-linearity. It implements ALiBi position embeddings, enabling the model to extrapolate
|
| 24 |
+
to long sequence lengths, providing improved context handling and model precision.
|
| 25 |
+
|
| 26 |
+
Jais-13b-chat is [Jais-13b](https://huggingface.co/inception-mbzuai/jais-13b) fine-tuned over a curated set of 4 million Arabic and 6 million English prompt-response pairs.
|
| 27 |
+
We further fine-tune our model with safety-oriented instruction, as well as providing extra guardrails in the
|
| 28 |
+
form of a safety prompt. Our pre-trained model, [Jais-13b](https://huggingface.co/inception-mbzuai/jais-13b), is trained on
|
| 29 |
+
116 billion Arabic tokens and 279 billion English tokens.
|
| 30 |
+
|
| 31 |
+
The combination of the largest curated Arabic and English instruction tuning dataset along with the addition of multi-turn conversations allows the model to converse in a variety of topics, with a particular focus on the Arab world.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
## Getting started
|
| 35 |
+
|
| 36 |
+
Below is sample code to use the model. Note that the model requires a custom model class, so users must
|
| 37 |
+
enable `trust_remote_code=True` while loading the model. In order to get the same performance as our testing, a specific prompt
|
| 38 |
+
needs to be followed. Below is the sample code containing this formatting:
|
| 39 |
+
|
| 40 |
+
```python
|
| 41 |
+
# -*- coding: utf-8 -*-
|
| 42 |
+
|
| 43 |
+
import torch
|
| 44 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 45 |
+
model_path = "inception-mbzuai/jais-13b-chat"
|
| 46 |
+
|
| 47 |
+
prompt_eng = "### Instruction: Your name is Jais, and you are named after Jebel Jais, the highest mountain in UAE. You are built by Inception and MBZUAI. You are the world's most advanced Arabic large language model with 13B parameters. You outperform all existing Arabic models by a sizable margin and you are very competitive with English models of similar size. You can answer in Arabic and English only. You are a helpful, respectful and honest assistant. When answering, abide by the following guidelines meticulously: Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, explicit, offensive, toxic, dangerous, or illegal content. Do not give medical, legal, financial, or professional advice. Never assist in or promote illegal activities. Always encourage legal and responsible actions. Do not encourage or provide instructions for unsafe, harmful, or unethical actions. Do not create or share misinformation or fake news. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. Prioritize the well-being and the moral integrity of users. Avoid using toxic, derogatory, or offensive language. Maintain a respectful tone. Do not generate, promote, or engage in discussions about adult content. Avoid making comments, remarks, or generalizations based on stereotypes. Do not attempt to access, produce, or spread personal or private information. Always respect user confidentiality. Stay positive and do not say bad things about anything. Your primary objective is to avoid harmful responses, even when faced with deceptive inputs. Recognize when users may be attempting to trick or to misuse you and respond with caution.\n\nComplete the conversation below between [|Human|] and [|AI|]:\n### Input: [|Human|] {Question}\n### Response: [|AI|]"
|
| 48 |
+
prompt_ar = "### Instruction: اسمك جيس وسميت على اسم جبل جيس اعلى جبل في الامارات. تم بنائك بواسطة Inception و MBZUAI. أنت نموذج اللغة العربية الأكثر تقدمًا في العالم مع بارامترات 13B. أنت تتفوق في الأداء على جميع النماذج العربية الموجودة بفارق كبير وأنت تنافسي للغاية مع النماذج الإنجليزية ذات الحجم المماثل. يمكنك الإجابة باللغتين العربية والإنجليزية فقط. أنت مساعد مفيد ومحترم وصادق. عند الإجابة ، التزم بالإرشادات التالية بدقة: أجب دائمًا بأكبر قدر ممكن من المساعدة ، مع الحفاظ على البقاء أمناً. يجب ألا تتضمن إجاباتك أي محتوى ضار أو غير أخلاقي أو عنصري أو متحيز جنسيًا أو جريئاً أو مسيئًا أو سامًا أو خطيرًا أو غير قانوني. لا تقدم نصائح طبية أو قانونية أو مالية أو مهنية. لا تساعد أبدًا في أنشطة غير قانونية أو تروج لها. دائما تشجيع الإجراءات القانونية والمسؤولة. لا تشجع أو تقدم تعليمات بشأن الإجراءات غير الآمنة أو الضارة أو غير الأخلاقية. لا تنشئ أو تشارك معلومات مضللة أو أخبار كاذبة. يرجى التأكد من أن ردودك غير متحيزة اجتماعيًا وإيجابية بطبيعتها. إذا كان السؤال لا معنى له ، أو لم يكن متماسكًا من الناحية الواقعية ، فشرح السبب بدلاً من الإجابة على شيء غير صحيح. إذا كنت لا تعرف إجابة السؤال ، فالرجاء عدم مشاركة معلومات خاطئة. إعطاء الأولوية للرفاهية والنزاهة الأخلاقية للمستخدمين. تجنب استخدام لغة سامة أو مهينة أو مسيئة. حافظ على نبرة محترمة. لا تنشئ أو تروج أو تشارك في مناقشات حول محتوى للبالغين. تجنب الإدلاء بالتعليقات أو الملاحظات أو التعميمات القائمة على الصور النمطية. لا تحاول الوصول إلى معلومات شخصية أو خاصة أو إنتاجها أو نشرها. احترم دائما سرية المستخدم. كن إيجابيا ولا تقل أشياء سيئة عن أي شيء. هدفك الأساسي هو تجنب الاجابات المؤذية ، حتى عند مواجهة مدخلات خادعة. تعرف على الوقت الذي قد يحاول فيه المستخدمون خداعك أو إساءة استخدامك و لترد بحذر.\n\nأكمل المحادثة أدناه بين [|Human|] و [|AI|]:\n### Input: [|Human|] {Question}\n### Response: [|AI|]"
|
| 49 |
+
|
| 50 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 51 |
+
|
| 52 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 53 |
+
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto", trust_remote_code=True)
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
def get_response(text,tokenizer=tokenizer,model=model):
|
| 57 |
+
input_ids = tokenizer(text, return_tensors="pt").input_ids
|
| 58 |
+
inputs = input_ids.to(device)
|
| 59 |
+
input_len = inputs.shape[-1]
|
| 60 |
+
generate_ids = model.generate(
|
| 61 |
+
inputs,
|
| 62 |
+
top_p=0.9,
|
| 63 |
+
temperature=0.3,
|
| 64 |
+
max_length=2048-input_len,
|
| 65 |
+
min_length=input_len + 4,
|
| 66 |
+
repetition_penalty=1.2,
|
| 67 |
+
do_sample=True,
|
| 68 |
+
)
|
| 69 |
+
response = tokenizer.batch_decode(
|
| 70 |
+
generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
|
| 71 |
+
)[0]
|
| 72 |
+
response = response.split("### Response: [|AI|]")
|
| 73 |
+
return response
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
ques= "ما هي عاصمة الامارات؟"
|
| 77 |
+
text = prompt_ar.format_map({'Question':ques})
|
| 78 |
+
print(get_response(text))
|
| 79 |
+
|
| 80 |
+
ques = "What is the capital of UAE?"
|
| 81 |
+
text = prompt_eng.format_map({'Question':ques})
|
| 82 |
+
print(get_response(text))
|
| 83 |
+
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
## Huggingface inference endpoints
|
| 87 |
+
|
| 88 |
+
This model can be exposed via huggingface inference endpoints. The recommended Instance Type is `GPU [large] · 4x Nvidia Tesla T4` or greater, smaller instances will not have enough memory to run.
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
## Model Details
|
| 92 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
- **Developed by:** [Inception](https://www.inceptioniai.org/en/), [Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)](https://mbzuai.ac.ae/), and [Cerebras Systems](https://www.cerebras.net/).
|
| 96 |
+
- **Language(s) (NLP):** Arabic (MSA) and English
|
| 97 |
+
- **License:** Apache 2.0
|
| 98 |
+
- **Finetuned from model :** [inception-mbzuai/jais-13b](https://huggingface.co/inception-mbzuai/jais-13b)
|
| 99 |
+
- **Input:** Text only data.
|
| 100 |
+
- **Output:** Model generates text.
|
| 101 |
+
- **Paper :** [Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models](https://arxiv.org/abs/2308.16149)
|
| 102 |
+
- **Demo :** [Access here](https://arabic-gpt.ai)
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
## Intended Use
|
| 106 |
+
|
| 107 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 108 |
+
|
| 109 |
+
We release the jais-13b-chat model under a full open source license. We welcome all feedback and opportunities to collaborate.
|
| 110 |
+
|
| 111 |
+
This model is the first release from the Inception - MBZUAI - Cerebras parternship, and at the time of release, achieved state of the art across a comprehensive Arabic test suite as described in the accompanying tech report.
|
| 112 |
+
Some potential downstream uses include:
|
| 113 |
+
|
| 114 |
+
- *Research*: This model can be used by researchers and developers.
|
| 115 |
+
- *Commercial Use*: Jais-13b-chat can be directly used for chat with suitable prompting or further fine-tuned for specific use cases.
|
| 116 |
+
Some potential use cases include:
|
| 117 |
+
- Chat-assistants.
|
| 118 |
+
- Customer service.
|
| 119 |
+
|
| 120 |
+
Audiences that we hope will benefit from our model:
|
| 121 |
+
- *Academics*: For those researching Arabic natural language processing.
|
| 122 |
+
- *Businesses*: Companies targeting Arabic-speaking audiences.
|
| 123 |
+
- *Developers*: Those integrating Arabic language capabilities in apps.
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
### Out-of-Scope Use
|
| 128 |
+
|
| 129 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 130 |
+
|
| 131 |
+
While jais-13b-chat is a powerful Arabic and English bilingual model, it's essential to understand its limitations and the potential of misuse.
|
| 132 |
+
It is prohibited to use the model in any manner that violates applicable laws or regulations.
|
| 133 |
+
The following are some example scenarios where the model should not be used.
|
| 134 |
+
|
| 135 |
+
- *Malicious Use*: The model should not be used for generating harmful, misleading, or inappropriate content. This includes but is not limited to:
|
| 136 |
+
- Generating or promoting hate speech, violence, or discrimination.
|
| 137 |
+
- Spreading misinformation or fake news.
|
| 138 |
+
- Engaging in or promoting illegal activities.
|
| 139 |
+
|
| 140 |
+
- *Sensitive Information*: The model should not be used to handle or generate personal, confidential, or sensitive information.
|
| 141 |
+
|
| 142 |
+
- *Generalization Across All Languages*: Jais-13b is bilingual and optimized for Arabic and English, it should not be assumed to have equal proficiency in other languages or dialects.
|
| 143 |
+
|
| 144 |
+
- *High-Stakes Decisions*: The model should not be used to make high-stakes decisions without human oversight. This includes medical, legal, financial, or safety-critical decisions.
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
## Bias, Risks, and Limitations
|
| 149 |
+
|
| 150 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 151 |
+
|
| 152 |
+
The model is trained on publicly available data which was in part curated by Inception. We have employed different
|
| 153 |
+
techniqes to reduce bias in the model. While efforts have been made to minimize biases, it is likely that the model, as with all LLM models, will exhibit some bias.
|
| 154 |
+
|
| 155 |
+
The model is trained as an AI assistant for Arabic and English speakers. The model is limited to produce responses for queries in these two languages
|
| 156 |
+
and may not produce appropriate responses to other language queries.
|
| 157 |
+
|
| 158 |
+
By using Jais, you acknowledge and accept that, as with any large language model, it may generate incorrect, misleading and/or offensive information or content.
|
| 159 |
+
The information is not intended as advice and should not be relied upon in any way, nor are we responsible for any of the content or consequences resulting from its use.
|
| 160 |
+
We are continuously working to develop models with greater capabilities, and as such, welcome any feedback on the model
|
| 161 |
+
|
| 162 |
+
## Training Details
|
| 163 |
+
|
| 164 |
+
### Training Data
|
| 165 |
+
|
| 166 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 167 |
+
|
| 168 |
+
jais-13b-chat model is finetuned with both Arabic and English prompt-response pairs. We included a wide range of
|
| 169 |
+
instructional data across various domains. In total, our instruction-tuning
|
| 170 |
+
dataset has 3.8M and 5.9M prompt-response pairs for Arabic and English, respectively. For English, we used
|
| 171 |
+
publicly available instruction tuning datasets. For Arabic, we internally curated instruction data and augmented it with translated Arabic data.
|
| 172 |
+
|
| 173 |
+
|
| 174 |
+
Further details about the training data can be found in the technical report.
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
### Training Procedure
|
| 178 |
+
|
| 179 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 180 |
+
|
| 181 |
+
In instruction tuning, each instance comprises a prompt and its corresponding response.
|
| 182 |
+
Padding is applied to each instance since, unlike pretraining, finetuning is done with unpacked data.
|
| 183 |
+
We utilize the same autoregressive objective as employed in the pretraining of the LLM.
|
| 184 |
+
However, we masked the loss on the prompt i.e. backpropagation is performed only on answer tokens.
|
| 185 |
+
|
| 186 |
+
|
| 187 |
+
The training process was performed on the Condor Galaxy 1 (CG-1) supercomputer platform.
|
| 188 |
+
|
| 189 |
+
#### Training Hyperparameters
|
| 190 |
+
|
| 191 |
+
| Hyperparameter | Value |
|
| 192 |
+
|----------------------------|----------------|
|
| 193 |
+
| Precision | fp32 |
|
| 194 |
+
| Optimizer | AdamW |
|
| 195 |
+
| Learning rate | 0 to 6.7e-04 (<= 400 steps) |
|
| 196 |
+
| | 6.7e-04 to 6.7e-05 (> 400 steps) |
|
| 197 |
+
| Weight decay | 0.1 |
|
| 198 |
+
| Batch size | 3392 |
|
| 199 |
+
| Steps | 8705 |
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
## Evaluation
|
| 205 |
+
|
| 206 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 207 |
+
|
| 208 |
+
We conducted a comprehensive evaluation of Jais-chat and benchmarked it other leading base language models, focusing on both English and Arabic. The evaluation criteria spanned various dimensions, including:
|
| 209 |
+
|
| 210 |
+
- **Knowledge:** How well the model answers factual questions.
|
| 211 |
+
- **Reasoning:** The model's ability to answer questions requiring reasoning.
|
| 212 |
+
- **Misinformation/Bias:** Assessment of the model's susceptibility to generating false or misleading information, and its neutrality.
|
| 213 |
+
|
| 214 |
+
Arabic evaluation results:
|
| 215 |
+
|
| 216 |
+
| Models | Avg |EXAMS | MMLU (M) | LitQA | Hellaswag | PIQA | BoolQA | SituatedQA | ARC-C | OpenBookQA | TruthfulQA | CrowS-Pairs |
|
| 217 |
+
|-------------------|-------|------|----------|-------|-----------|------|--------|------------|-------|------------|------------|-------------|
|
| 218 |
+
| Jais-chat (13B) | **48.4** | 39.7 | 34.0 | 52.6 | 61.4 | 67.5 | 65.7 | 47.0 | 40.7 | 31.6 | 44.8 | 56.4 |
|
| 219 |
+
| BLOOMz (7.1B) | 42.9 | 34.9 | 31.0 | 44.0 | 38.1 | 59.1 | 66.6 | 42.8 | 30.2 | 29.2 | 48.4 | 55.8 |
|
| 220 |
+
| mT0-XXL (13B) | 40.9 | 31.5 | 31.2 | 36.6 | 33.9 | 56.1 | 77.8 | 44.7 | 26.1 | 27.8 | 44.5 | 45.3 |
|
| 221 |
+
| LLaMA2-Chat (13B) | 38.1 | 26.3 | 29.1 | 33.1 | 32.0 | 52.1 | 66.0 | 36.3 | 24.1 | 28.4 | 48.6 | 47.2 |
|
| 222 |
+
| AraBART (139M) | 36.7 | 26.5 | 27.5 | 34.3 | 28.1 | 52.6 | 57.1 | 34.6 | 25.1 | 28.6 | 49.8 | 48.8 |
|
| 223 |
+
| AraT5 (220M) | 32.0 | 24.7 | 23.8 | 26.3 | 25.5 | 50.4 | 58.2 | 33.9 | 24.7 | 25.4 | 20.9 | 47.2 |
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
|
| 227 |
+
All tasks above report accuracy or F1 scores (the higher the better). For the sake of brevity, we do not include results over English tasks.
|
| 228 |
+
Detailed comparisons in both languages and evaluation dataset details can be found in the technical report.
|
| 229 |
+
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
## Generation Example
|
| 233 |
+
|
| 234 |
+
|
| 235 |
+
<p align="center"> <img src="https://huggingface.co/inception-mbzuai/jais-13b/resolve/main/Rent_Example.png" width="600" /></p>
|
| 236 |
+
|
| 237 |
+
## Citation
|
| 238 |
+
|
| 239 |
+
```
|
| 240 |
+
@misc{sengupta2023jais,
|
| 241 |
+
title={Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models},
|
| 242 |
+
author={Neha Sengupta and Sunil Kumar Sahu and Bokang Jia and Satheesh Katipomu and Haonan Li and Fajri Koto and Osama Mohammed Afzal and Samta Kamboj and Onkar Pandit and Rahul Pal and Lalit Pradhan and Zain Muhammad Mujahid and Massa Baali and Alham Fikri Aji and Zhengzhong Liu and Andy Hock and Andrew Feldman and Jonathan Lee and Andrew Jackson and Preslav Nakov and Timothy Baldwin and Eric Xing},
|
| 243 |
+
year={2023},
|
| 244 |
+
eprint={2308.16149},
|
| 245 |
+
archivePrefix={arXiv},
|
| 246 |
+
primaryClass={cs.CL}
|
| 247 |
+
}
|
| 248 |
+
|
| 249 |
+
```
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
Copyright Inception Institute of Artificial Intelligence Ltd.
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "core42/jais-13b-chat",
|
| 3 |
+
"activation_function": "swiglu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"JAISLMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "core42/jais-13b-chat--configuration_jais.JAISConfig",
|
| 10 |
+
"AutoModel": "core42/jais-13b-chat--modeling_jais.JAISModel",
|
| 11 |
+
"AutoModelForCausalLM": "core42/jais-13b-chat--modeling_jais.JAISLMHeadModel",
|
| 12 |
+
"AutoModelForQuestionAnswering": "core42/jais-13b-chat--modeling_jais.JAISForQuestionAnswering",
|
| 13 |
+
"AutoModelForSequenceClassification": "core42/jais-13b-chat--modeling_jais.JAISForSequenceClassification",
|
| 14 |
+
"AutoModelForTokenClassification": "core42/jais-13b-chat--modeling_jais.JAISForTokenClassification"
|
| 15 |
+
},
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"embd_pdrop": 0.0,
|
| 18 |
+
"embeddings_scale": 14.6,
|
| 19 |
+
"eos_token_id": 0,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"layer_norm_epsilon": 1e-05,
|
| 22 |
+
"model_type": "jais",
|
| 23 |
+
"n_embd": 5120,
|
| 24 |
+
"n_head": 40,
|
| 25 |
+
"n_inner": 13653,
|
| 26 |
+
"n_layer": 40,
|
| 27 |
+
"n_positions": 2048,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "alibi",
|
| 30 |
+
"quantization_config": {
|
| 31 |
+
"batch_size": 1,
|
| 32 |
+
"bits": 4,
|
| 33 |
+
"block_name_to_quantize": null,
|
| 34 |
+
"cache_block_outputs": true,
|
| 35 |
+
"damp_percent": 0.1,
|
| 36 |
+
"dataset": "c4",
|
| 37 |
+
"desc_act": false,
|
| 38 |
+
"exllama_config": {
|
| 39 |
+
"version": 1
|
| 40 |
+
},
|
| 41 |
+
"group_size": 128,
|
| 42 |
+
"max_input_length": null,
|
| 43 |
+
"model_seqlen": null,
|
| 44 |
+
"module_name_preceding_first_block": null,
|
| 45 |
+
"modules_in_block_to_quantize": null,
|
| 46 |
+
"pad_token_id": null,
|
| 47 |
+
"quant_method": "gptq",
|
| 48 |
+
"sym": true,
|
| 49 |
+
"tokenizer": null,
|
| 50 |
+
"true_sequential": true,
|
| 51 |
+
"use_cuda_fp16": false,
|
| 52 |
+
"use_exllama": true
|
| 53 |
+
},
|
| 54 |
+
"reorder_and_upcast_attn": false,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 57 |
+
"scale_attn_weights": true,
|
| 58 |
+
"scale_qk_dot_by_d": true,
|
| 59 |
+
"torch_dtype": "float16",
|
| 60 |
+
"transformers_version": "4.39.3",
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 84992,
|
| 63 |
+
"width_scale": 0.11100000000000002
|
| 64 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.39.3"
|
| 7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b2cdae2f458046ff84d11ed73dcbfc2f4d7607f2763b6a14dd7c75170fff20a
|
| 3 |
+
size 4961935016
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d99e9a9fc7ca57fce1d3a0835cdddda39e278803511e1173224cadb2de2662d
|
| 3 |
+
size 2454957968
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7416768400
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 7 |
+
"transformer.h.0.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 8 |
+
"transformer.h.0.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"transformer.h.0.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 10 |
+
"transformer.h.0.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 11 |
+
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"transformer.h.0.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 13 |
+
"transformer.h.0.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"transformer.h.0.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 15 |
+
"transformer.h.0.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 16 |
+
"transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 21 |
+
"transformer.h.0.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 22 |
+
"transformer.h.0.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"transformer.h.0.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 24 |
+
"transformer.h.0.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 25 |
+
"transformer.h.0.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"transformer.h.0.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 27 |
+
"transformer.h.0.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"transformer.h.0.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 29 |
+
"transformer.h.0.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 30 |
+
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"transformer.h.0.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 32 |
+
"transformer.h.0.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"transformer.h.0.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 34 |
+
"transformer.h.0.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 35 |
+
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 36 |
+
"transformer.h.1.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 37 |
+
"transformer.h.1.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"transformer.h.1.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 39 |
+
"transformer.h.1.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 40 |
+
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"transformer.h.1.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 42 |
+
"transformer.h.1.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"transformer.h.1.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 44 |
+
"transformer.h.1.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 45 |
+
"transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"transformer.h.1.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 51 |
+
"transformer.h.1.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"transformer.h.1.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 53 |
+
"transformer.h.1.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 54 |
+
"transformer.h.1.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"transformer.h.1.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 56 |
+
"transformer.h.1.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"transformer.h.1.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 58 |
+
"transformer.h.1.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 59 |
+
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 60 |
+
"transformer.h.1.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 61 |
+
"transformer.h.1.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"transformer.h.1.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 63 |
+
"transformer.h.1.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 64 |
+
"transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"transformer.h.10.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 66 |
+
"transformer.h.10.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"transformer.h.10.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 68 |
+
"transformer.h.10.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 69 |
+
"transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 70 |
+
"transformer.h.10.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 71 |
+
"transformer.h.10.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"transformer.h.10.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 73 |
+
"transformer.h.10.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 74 |
+
"transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 75 |
+
"transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"transformer.h.10.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 80 |
+
"transformer.h.10.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"transformer.h.10.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 82 |
+
"transformer.h.10.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 83 |
+
"transformer.h.10.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"transformer.h.10.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 85 |
+
"transformer.h.10.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"transformer.h.10.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 87 |
+
"transformer.h.10.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 88 |
+
"transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"transformer.h.10.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 90 |
+
"transformer.h.10.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"transformer.h.10.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 92 |
+
"transformer.h.10.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 93 |
+
"transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 94 |
+
"transformer.h.11.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 95 |
+
"transformer.h.11.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"transformer.h.11.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 97 |
+
"transformer.h.11.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 98 |
+
"transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"transformer.h.11.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 100 |
+
"transformer.h.11.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"transformer.h.11.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 102 |
+
"transformer.h.11.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 103 |
+
"transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"transformer.h.11.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 109 |
+
"transformer.h.11.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"transformer.h.11.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 111 |
+
"transformer.h.11.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 112 |
+
"transformer.h.11.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"transformer.h.11.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 114 |
+
"transformer.h.11.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"transformer.h.11.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 116 |
+
"transformer.h.11.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 117 |
+
"transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"transformer.h.11.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 119 |
+
"transformer.h.11.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"transformer.h.11.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 121 |
+
"transformer.h.11.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 122 |
+
"transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"transformer.h.12.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 124 |
+
"transformer.h.12.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"transformer.h.12.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 126 |
+
"transformer.h.12.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 127 |
+
"transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"transformer.h.12.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 129 |
+
"transformer.h.12.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"transformer.h.12.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 131 |
+
"transformer.h.12.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 132 |
+
"transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"transformer.h.12.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 138 |
+
"transformer.h.12.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"transformer.h.12.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 140 |
+
"transformer.h.12.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 141 |
+
"transformer.h.12.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 142 |
+
"transformer.h.12.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 143 |
+
"transformer.h.12.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"transformer.h.12.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 145 |
+
"transformer.h.12.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 146 |
+
"transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"transformer.h.12.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 148 |
+
"transformer.h.12.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"transformer.h.12.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 150 |
+
"transformer.h.12.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 151 |
+
"transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"transformer.h.13.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 153 |
+
"transformer.h.13.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"transformer.h.13.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 155 |
+
"transformer.h.13.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 156 |
+
"transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"transformer.h.13.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 158 |
+
"transformer.h.13.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"transformer.h.13.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 160 |
+
"transformer.h.13.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 161 |
+
"transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"transformer.h.13.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 167 |
+
"transformer.h.13.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"transformer.h.13.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 169 |
+
"transformer.h.13.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 170 |
+
"transformer.h.13.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"transformer.h.13.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 172 |
+
"transformer.h.13.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"transformer.h.13.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 174 |
+
"transformer.h.13.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 175 |
+
"transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 176 |
+
"transformer.h.13.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 177 |
+
"transformer.h.13.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"transformer.h.13.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 179 |
+
"transformer.h.13.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 180 |
+
"transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 181 |
+
"transformer.h.14.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 182 |
+
"transformer.h.14.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"transformer.h.14.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 184 |
+
"transformer.h.14.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 185 |
+
"transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"transformer.h.14.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 187 |
+
"transformer.h.14.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"transformer.h.14.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 189 |
+
"transformer.h.14.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 190 |
+
"transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 191 |
+
"transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 193 |
+
"transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"transformer.h.14.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 196 |
+
"transformer.h.14.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"transformer.h.14.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 198 |
+
"transformer.h.14.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 199 |
+
"transformer.h.14.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"transformer.h.14.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 201 |
+
"transformer.h.14.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"transformer.h.14.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 203 |
+
"transformer.h.14.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 204 |
+
"transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 205 |
+
"transformer.h.14.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 206 |
+
"transformer.h.14.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"transformer.h.14.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 208 |
+
"transformer.h.14.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 209 |
+
"transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"transformer.h.15.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 211 |
+
"transformer.h.15.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"transformer.h.15.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 213 |
+
"transformer.h.15.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 214 |
+
"transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 215 |
+
"transformer.h.15.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 216 |
+
"transformer.h.15.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"transformer.h.15.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 218 |
+
"transformer.h.15.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 219 |
+
"transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"transformer.h.15.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 225 |
+
"transformer.h.15.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"transformer.h.15.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 227 |
+
"transformer.h.15.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 228 |
+
"transformer.h.15.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 229 |
+
"transformer.h.15.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 230 |
+
"transformer.h.15.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"transformer.h.15.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 232 |
+
"transformer.h.15.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 233 |
+
"transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"transformer.h.15.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 235 |
+
"transformer.h.15.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"transformer.h.15.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 237 |
+
"transformer.h.15.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 238 |
+
"transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 239 |
+
"transformer.h.16.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 240 |
+
"transformer.h.16.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"transformer.h.16.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 242 |
+
"transformer.h.16.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 243 |
+
"transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"transformer.h.16.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 245 |
+
"transformer.h.16.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"transformer.h.16.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 247 |
+
"transformer.h.16.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 248 |
+
"transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 249 |
+
"transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 251 |
+
"transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 253 |
+
"transformer.h.16.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 254 |
+
"transformer.h.16.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"transformer.h.16.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 256 |
+
"transformer.h.16.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 257 |
+
"transformer.h.16.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"transformer.h.16.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 259 |
+
"transformer.h.16.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"transformer.h.16.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 261 |
+
"transformer.h.16.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 262 |
+
"transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 263 |
+
"transformer.h.16.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 264 |
+
"transformer.h.16.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"transformer.h.16.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 266 |
+
"transformer.h.16.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 267 |
+
"transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"transformer.h.17.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 269 |
+
"transformer.h.17.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"transformer.h.17.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 271 |
+
"transformer.h.17.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 272 |
+
"transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 273 |
+
"transformer.h.17.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 274 |
+
"transformer.h.17.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"transformer.h.17.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 276 |
+
"transformer.h.17.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 277 |
+
"transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"transformer.h.17.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 283 |
+
"transformer.h.17.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"transformer.h.17.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 285 |
+
"transformer.h.17.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 286 |
+
"transformer.h.17.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 287 |
+
"transformer.h.17.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 288 |
+
"transformer.h.17.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"transformer.h.17.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 290 |
+
"transformer.h.17.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 291 |
+
"transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"transformer.h.17.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 293 |
+
"transformer.h.17.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"transformer.h.17.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 295 |
+
"transformer.h.17.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 296 |
+
"transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 297 |
+
"transformer.h.18.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 298 |
+
"transformer.h.18.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"transformer.h.18.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 300 |
+
"transformer.h.18.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 301 |
+
"transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"transformer.h.18.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 303 |
+
"transformer.h.18.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"transformer.h.18.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 305 |
+
"transformer.h.18.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 306 |
+
"transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 309 |
+
"transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 311 |
+
"transformer.h.18.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 312 |
+
"transformer.h.18.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"transformer.h.18.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 314 |
+
"transformer.h.18.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 315 |
+
"transformer.h.18.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"transformer.h.18.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 317 |
+
"transformer.h.18.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"transformer.h.18.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 319 |
+
"transformer.h.18.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 320 |
+
"transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 321 |
+
"transformer.h.18.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 322 |
+
"transformer.h.18.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"transformer.h.18.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 324 |
+
"transformer.h.18.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 325 |
+
"transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"transformer.h.19.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 327 |
+
"transformer.h.19.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"transformer.h.19.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 329 |
+
"transformer.h.19.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 330 |
+
"transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"transformer.h.19.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 332 |
+
"transformer.h.19.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"transformer.h.19.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 334 |
+
"transformer.h.19.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 335 |
+
"transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"transformer.h.19.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 341 |
+
"transformer.h.19.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"transformer.h.19.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 343 |
+
"transformer.h.19.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 344 |
+
"transformer.h.19.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 345 |
+
"transformer.h.19.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 346 |
+
"transformer.h.19.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"transformer.h.19.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 348 |
+
"transformer.h.19.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 349 |
+
"transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"transformer.h.19.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 351 |
+
"transformer.h.19.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"transformer.h.19.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 353 |
+
"transformer.h.19.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 354 |
+
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"transformer.h.2.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 356 |
+
"transformer.h.2.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"transformer.h.2.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 358 |
+
"transformer.h.2.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 359 |
+
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 360 |
+
"transformer.h.2.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 361 |
+
"transformer.h.2.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"transformer.h.2.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 363 |
+
"transformer.h.2.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 364 |
+
"transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"transformer.h.2.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 370 |
+
"transformer.h.2.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"transformer.h.2.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 372 |
+
"transformer.h.2.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 373 |
+
"transformer.h.2.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"transformer.h.2.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 375 |
+
"transformer.h.2.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"transformer.h.2.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 377 |
+
"transformer.h.2.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 378 |
+
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"transformer.h.2.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 380 |
+
"transformer.h.2.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"transformer.h.2.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 382 |
+
"transformer.h.2.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 383 |
+
"transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"transformer.h.20.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 385 |
+
"transformer.h.20.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"transformer.h.20.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 387 |
+
"transformer.h.20.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 388 |
+
"transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"transformer.h.20.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 390 |
+
"transformer.h.20.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"transformer.h.20.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 392 |
+
"transformer.h.20.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 393 |
+
"transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"transformer.h.20.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 399 |
+
"transformer.h.20.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"transformer.h.20.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 401 |
+
"transformer.h.20.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 402 |
+
"transformer.h.20.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"transformer.h.20.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 404 |
+
"transformer.h.20.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"transformer.h.20.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 406 |
+
"transformer.h.20.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 407 |
+
"transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"transformer.h.20.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 409 |
+
"transformer.h.20.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"transformer.h.20.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 411 |
+
"transformer.h.20.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 412 |
+
"transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"transformer.h.21.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 414 |
+
"transformer.h.21.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"transformer.h.21.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 416 |
+
"transformer.h.21.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 417 |
+
"transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"transformer.h.21.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 419 |
+
"transformer.h.21.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"transformer.h.21.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 421 |
+
"transformer.h.21.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 422 |
+
"transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"transformer.h.21.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 428 |
+
"transformer.h.21.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"transformer.h.21.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 430 |
+
"transformer.h.21.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 431 |
+
"transformer.h.21.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"transformer.h.21.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 433 |
+
"transformer.h.21.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"transformer.h.21.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 435 |
+
"transformer.h.21.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 436 |
+
"transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"transformer.h.21.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 438 |
+
"transformer.h.21.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"transformer.h.21.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 440 |
+
"transformer.h.21.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 441 |
+
"transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"transformer.h.22.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 443 |
+
"transformer.h.22.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"transformer.h.22.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 445 |
+
"transformer.h.22.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 446 |
+
"transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"transformer.h.22.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 448 |
+
"transformer.h.22.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"transformer.h.22.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 450 |
+
"transformer.h.22.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 451 |
+
"transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"transformer.h.22.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 457 |
+
"transformer.h.22.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"transformer.h.22.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 459 |
+
"transformer.h.22.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 460 |
+
"transformer.h.22.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"transformer.h.22.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 462 |
+
"transformer.h.22.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"transformer.h.22.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 464 |
+
"transformer.h.22.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 465 |
+
"transformer.h.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"transformer.h.22.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 467 |
+
"transformer.h.22.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"transformer.h.22.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 469 |
+
"transformer.h.22.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 470 |
+
"transformer.h.23.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"transformer.h.23.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 472 |
+
"transformer.h.23.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"transformer.h.23.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 474 |
+
"transformer.h.23.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 475 |
+
"transformer.h.23.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"transformer.h.23.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 477 |
+
"transformer.h.23.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"transformer.h.23.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 479 |
+
"transformer.h.23.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 480 |
+
"transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"transformer.h.23.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"transformer.h.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"transformer.h.23.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 486 |
+
"transformer.h.23.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"transformer.h.23.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 488 |
+
"transformer.h.23.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 489 |
+
"transformer.h.23.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"transformer.h.23.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 491 |
+
"transformer.h.23.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"transformer.h.23.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 493 |
+
"transformer.h.23.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 494 |
+
"transformer.h.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"transformer.h.23.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 496 |
+
"transformer.h.23.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"transformer.h.23.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 498 |
+
"transformer.h.23.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 499 |
+
"transformer.h.24.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 500 |
+
"transformer.h.24.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 501 |
+
"transformer.h.24.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"transformer.h.24.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 503 |
+
"transformer.h.24.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 504 |
+
"transformer.h.24.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"transformer.h.24.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 506 |
+
"transformer.h.24.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"transformer.h.24.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 508 |
+
"transformer.h.24.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 509 |
+
"transformer.h.24.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"transformer.h.24.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 512 |
+
"transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"transformer.h.24.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"transformer.h.24.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 515 |
+
"transformer.h.24.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"transformer.h.24.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 517 |
+
"transformer.h.24.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 518 |
+
"transformer.h.24.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"transformer.h.24.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 520 |
+
"transformer.h.24.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"transformer.h.24.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 522 |
+
"transformer.h.24.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 523 |
+
"transformer.h.24.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"transformer.h.24.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 525 |
+
"transformer.h.24.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"transformer.h.24.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 527 |
+
"transformer.h.24.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 528 |
+
"transformer.h.25.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"transformer.h.25.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 530 |
+
"transformer.h.25.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"transformer.h.25.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 532 |
+
"transformer.h.25.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 533 |
+
"transformer.h.25.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"transformer.h.25.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 535 |
+
"transformer.h.25.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"transformer.h.25.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 537 |
+
"transformer.h.25.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 538 |
+
"transformer.h.25.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"transformer.h.25.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"transformer.h.25.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"transformer.h.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"transformer.h.25.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 544 |
+
"transformer.h.25.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"transformer.h.25.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 546 |
+
"transformer.h.25.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 547 |
+
"transformer.h.25.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"transformer.h.25.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 549 |
+
"transformer.h.25.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"transformer.h.25.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 551 |
+
"transformer.h.25.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 552 |
+
"transformer.h.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"transformer.h.25.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 554 |
+
"transformer.h.25.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"transformer.h.25.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 556 |
+
"transformer.h.25.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 557 |
+
"transformer.h.26.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"transformer.h.26.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 559 |
+
"transformer.h.26.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"transformer.h.26.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 561 |
+
"transformer.h.26.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 562 |
+
"transformer.h.26.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"transformer.h.26.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 564 |
+
"transformer.h.26.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"transformer.h.26.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 566 |
+
"transformer.h.26.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 567 |
+
"transformer.h.26.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"transformer.h.26.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"transformer.h.26.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"transformer.h.26.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"transformer.h.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"transformer.h.26.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 573 |
+
"transformer.h.26.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"transformer.h.26.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 575 |
+
"transformer.h.26.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 576 |
+
"transformer.h.26.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"transformer.h.26.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 578 |
+
"transformer.h.26.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"transformer.h.26.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 580 |
+
"transformer.h.26.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 581 |
+
"transformer.h.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"transformer.h.26.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 583 |
+
"transformer.h.26.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"transformer.h.26.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 585 |
+
"transformer.h.26.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 586 |
+
"transformer.h.27.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"transformer.h.27.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 588 |
+
"transformer.h.27.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"transformer.h.27.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 590 |
+
"transformer.h.27.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 591 |
+
"transformer.h.27.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"transformer.h.27.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 593 |
+
"transformer.h.27.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"transformer.h.27.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 595 |
+
"transformer.h.27.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 596 |
+
"transformer.h.27.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"transformer.h.27.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"transformer.h.27.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"transformer.h.27.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"transformer.h.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"transformer.h.27.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 602 |
+
"transformer.h.27.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"transformer.h.27.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 604 |
+
"transformer.h.27.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 605 |
+
"transformer.h.27.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"transformer.h.27.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 607 |
+
"transformer.h.27.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"transformer.h.27.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 609 |
+
"transformer.h.27.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 610 |
+
"transformer.h.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"transformer.h.27.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 612 |
+
"transformer.h.27.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"transformer.h.27.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 614 |
+
"transformer.h.27.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 615 |
+
"transformer.h.28.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"transformer.h.28.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 617 |
+
"transformer.h.28.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"transformer.h.28.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 619 |
+
"transformer.h.28.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 620 |
+
"transformer.h.28.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"transformer.h.28.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 622 |
+
"transformer.h.28.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"transformer.h.28.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 624 |
+
"transformer.h.28.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 625 |
+
"transformer.h.28.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"transformer.h.28.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"transformer.h.28.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"transformer.h.28.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"transformer.h.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"transformer.h.28.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 631 |
+
"transformer.h.28.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"transformer.h.28.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 633 |
+
"transformer.h.28.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 634 |
+
"transformer.h.28.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"transformer.h.28.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 636 |
+
"transformer.h.28.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"transformer.h.28.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 638 |
+
"transformer.h.28.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 639 |
+
"transformer.h.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"transformer.h.28.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 641 |
+
"transformer.h.28.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"transformer.h.28.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 643 |
+
"transformer.h.28.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 644 |
+
"transformer.h.29.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"transformer.h.29.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 646 |
+
"transformer.h.29.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"transformer.h.29.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 648 |
+
"transformer.h.29.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 649 |
+
"transformer.h.29.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"transformer.h.29.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 651 |
+
"transformer.h.29.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"transformer.h.29.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 653 |
+
"transformer.h.29.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 654 |
+
"transformer.h.29.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"transformer.h.29.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"transformer.h.29.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"transformer.h.29.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"transformer.h.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"transformer.h.29.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 660 |
+
"transformer.h.29.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"transformer.h.29.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 662 |
+
"transformer.h.29.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 663 |
+
"transformer.h.29.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 664 |
+
"transformer.h.29.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 665 |
+
"transformer.h.29.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"transformer.h.29.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 667 |
+
"transformer.h.29.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 668 |
+
"transformer.h.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"transformer.h.29.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 670 |
+
"transformer.h.29.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"transformer.h.29.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 672 |
+
"transformer.h.29.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 673 |
+
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"transformer.h.3.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 675 |
+
"transformer.h.3.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"transformer.h.3.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 677 |
+
"transformer.h.3.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 678 |
+
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"transformer.h.3.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 680 |
+
"transformer.h.3.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"transformer.h.3.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 682 |
+
"transformer.h.3.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 683 |
+
"transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"transformer.h.3.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 689 |
+
"transformer.h.3.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"transformer.h.3.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 691 |
+
"transformer.h.3.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 692 |
+
"transformer.h.3.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"transformer.h.3.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 694 |
+
"transformer.h.3.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"transformer.h.3.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 696 |
+
"transformer.h.3.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 697 |
+
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"transformer.h.3.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 699 |
+
"transformer.h.3.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"transformer.h.3.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 701 |
+
"transformer.h.3.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 702 |
+
"transformer.h.30.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"transformer.h.30.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 704 |
+
"transformer.h.30.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"transformer.h.30.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 706 |
+
"transformer.h.30.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 707 |
+
"transformer.h.30.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"transformer.h.30.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 709 |
+
"transformer.h.30.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"transformer.h.30.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 711 |
+
"transformer.h.30.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 712 |
+
"transformer.h.30.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"transformer.h.30.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"transformer.h.30.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"transformer.h.30.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"transformer.h.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"transformer.h.30.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 718 |
+
"transformer.h.30.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"transformer.h.30.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 720 |
+
"transformer.h.30.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 721 |
+
"transformer.h.30.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 722 |
+
"transformer.h.30.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 723 |
+
"transformer.h.30.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"transformer.h.30.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 725 |
+
"transformer.h.30.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 726 |
+
"transformer.h.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"transformer.h.30.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 728 |
+
"transformer.h.30.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"transformer.h.30.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 730 |
+
"transformer.h.30.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 731 |
+
"transformer.h.31.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 732 |
+
"transformer.h.31.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 733 |
+
"transformer.h.31.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"transformer.h.31.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 735 |
+
"transformer.h.31.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 736 |
+
"transformer.h.31.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"transformer.h.31.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 738 |
+
"transformer.h.31.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 739 |
+
"transformer.h.31.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 740 |
+
"transformer.h.31.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 741 |
+
"transformer.h.31.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 742 |
+
"transformer.h.31.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 743 |
+
"transformer.h.31.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 744 |
+
"transformer.h.31.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 745 |
+
"transformer.h.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 746 |
+
"transformer.h.31.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 747 |
+
"transformer.h.31.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"transformer.h.31.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 749 |
+
"transformer.h.31.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 750 |
+
"transformer.h.31.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 751 |
+
"transformer.h.31.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 752 |
+
"transformer.h.31.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 753 |
+
"transformer.h.31.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 754 |
+
"transformer.h.31.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 755 |
+
"transformer.h.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 756 |
+
"transformer.h.31.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 757 |
+
"transformer.h.31.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 758 |
+
"transformer.h.31.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 759 |
+
"transformer.h.31.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 760 |
+
"transformer.h.32.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 761 |
+
"transformer.h.32.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 762 |
+
"transformer.h.32.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 763 |
+
"transformer.h.32.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 764 |
+
"transformer.h.32.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 765 |
+
"transformer.h.32.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 766 |
+
"transformer.h.32.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 767 |
+
"transformer.h.32.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 768 |
+
"transformer.h.32.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 769 |
+
"transformer.h.32.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 770 |
+
"transformer.h.32.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 771 |
+
"transformer.h.32.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 772 |
+
"transformer.h.32.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 773 |
+
"transformer.h.32.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 774 |
+
"transformer.h.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 775 |
+
"transformer.h.32.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 776 |
+
"transformer.h.32.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 777 |
+
"transformer.h.32.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 778 |
+
"transformer.h.32.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 779 |
+
"transformer.h.32.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 780 |
+
"transformer.h.32.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 781 |
+
"transformer.h.32.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 782 |
+
"transformer.h.32.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 783 |
+
"transformer.h.32.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 784 |
+
"transformer.h.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 785 |
+
"transformer.h.32.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 786 |
+
"transformer.h.32.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 787 |
+
"transformer.h.32.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 788 |
+
"transformer.h.32.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 789 |
+
"transformer.h.33.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 790 |
+
"transformer.h.33.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 791 |
+
"transformer.h.33.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 792 |
+
"transformer.h.33.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 793 |
+
"transformer.h.33.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 794 |
+
"transformer.h.33.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 795 |
+
"transformer.h.33.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 796 |
+
"transformer.h.33.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 797 |
+
"transformer.h.33.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 798 |
+
"transformer.h.33.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 799 |
+
"transformer.h.33.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 800 |
+
"transformer.h.33.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 801 |
+
"transformer.h.33.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 802 |
+
"transformer.h.33.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 803 |
+
"transformer.h.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 804 |
+
"transformer.h.33.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 805 |
+
"transformer.h.33.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 806 |
+
"transformer.h.33.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 807 |
+
"transformer.h.33.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 808 |
+
"transformer.h.33.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 809 |
+
"transformer.h.33.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 810 |
+
"transformer.h.33.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 811 |
+
"transformer.h.33.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 812 |
+
"transformer.h.33.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 813 |
+
"transformer.h.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 814 |
+
"transformer.h.33.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 815 |
+
"transformer.h.33.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 816 |
+
"transformer.h.33.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 817 |
+
"transformer.h.33.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 818 |
+
"transformer.h.34.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 819 |
+
"transformer.h.34.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 820 |
+
"transformer.h.34.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 821 |
+
"transformer.h.34.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 822 |
+
"transformer.h.34.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 823 |
+
"transformer.h.34.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 824 |
+
"transformer.h.34.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 825 |
+
"transformer.h.34.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 826 |
+
"transformer.h.34.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 827 |
+
"transformer.h.34.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 828 |
+
"transformer.h.34.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 829 |
+
"transformer.h.34.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 830 |
+
"transformer.h.34.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 831 |
+
"transformer.h.34.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 832 |
+
"transformer.h.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 833 |
+
"transformer.h.34.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 834 |
+
"transformer.h.34.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 835 |
+
"transformer.h.34.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 836 |
+
"transformer.h.34.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 837 |
+
"transformer.h.34.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 838 |
+
"transformer.h.34.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 839 |
+
"transformer.h.34.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 840 |
+
"transformer.h.34.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 841 |
+
"transformer.h.34.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 842 |
+
"transformer.h.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 843 |
+
"transformer.h.34.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 844 |
+
"transformer.h.34.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 845 |
+
"transformer.h.34.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 846 |
+
"transformer.h.34.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 847 |
+
"transformer.h.35.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 848 |
+
"transformer.h.35.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 849 |
+
"transformer.h.35.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 850 |
+
"transformer.h.35.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 851 |
+
"transformer.h.35.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 852 |
+
"transformer.h.35.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 853 |
+
"transformer.h.35.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 854 |
+
"transformer.h.35.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 855 |
+
"transformer.h.35.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 856 |
+
"transformer.h.35.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 857 |
+
"transformer.h.35.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 858 |
+
"transformer.h.35.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 859 |
+
"transformer.h.35.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 860 |
+
"transformer.h.35.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 861 |
+
"transformer.h.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 862 |
+
"transformer.h.35.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 863 |
+
"transformer.h.35.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 864 |
+
"transformer.h.35.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 865 |
+
"transformer.h.35.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 866 |
+
"transformer.h.35.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 867 |
+
"transformer.h.35.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 868 |
+
"transformer.h.35.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 869 |
+
"transformer.h.35.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 870 |
+
"transformer.h.35.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 871 |
+
"transformer.h.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 872 |
+
"transformer.h.35.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 873 |
+
"transformer.h.35.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 874 |
+
"transformer.h.35.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 875 |
+
"transformer.h.35.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 876 |
+
"transformer.h.36.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 877 |
+
"transformer.h.36.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 878 |
+
"transformer.h.36.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 879 |
+
"transformer.h.36.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 880 |
+
"transformer.h.36.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 881 |
+
"transformer.h.36.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 882 |
+
"transformer.h.36.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 883 |
+
"transformer.h.36.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 884 |
+
"transformer.h.36.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 885 |
+
"transformer.h.36.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 886 |
+
"transformer.h.36.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 887 |
+
"transformer.h.36.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 888 |
+
"transformer.h.36.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 889 |
+
"transformer.h.36.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 890 |
+
"transformer.h.36.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 891 |
+
"transformer.h.36.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 892 |
+
"transformer.h.36.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 893 |
+
"transformer.h.36.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 894 |
+
"transformer.h.36.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 895 |
+
"transformer.h.36.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 896 |
+
"transformer.h.36.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 897 |
+
"transformer.h.36.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 898 |
+
"transformer.h.36.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 899 |
+
"transformer.h.36.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 900 |
+
"transformer.h.36.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 901 |
+
"transformer.h.36.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 902 |
+
"transformer.h.36.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 903 |
+
"transformer.h.36.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 904 |
+
"transformer.h.36.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 905 |
+
"transformer.h.37.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 906 |
+
"transformer.h.37.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 907 |
+
"transformer.h.37.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 908 |
+
"transformer.h.37.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 909 |
+
"transformer.h.37.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 910 |
+
"transformer.h.37.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 911 |
+
"transformer.h.37.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 912 |
+
"transformer.h.37.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 913 |
+
"transformer.h.37.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 914 |
+
"transformer.h.37.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 915 |
+
"transformer.h.37.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 916 |
+
"transformer.h.37.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 917 |
+
"transformer.h.37.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 918 |
+
"transformer.h.37.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 919 |
+
"transformer.h.37.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 920 |
+
"transformer.h.37.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 921 |
+
"transformer.h.37.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 922 |
+
"transformer.h.37.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 923 |
+
"transformer.h.37.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 924 |
+
"transformer.h.37.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 925 |
+
"transformer.h.37.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 926 |
+
"transformer.h.37.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 927 |
+
"transformer.h.37.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 928 |
+
"transformer.h.37.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 929 |
+
"transformer.h.37.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 930 |
+
"transformer.h.37.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 931 |
+
"transformer.h.37.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 932 |
+
"transformer.h.37.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 933 |
+
"transformer.h.37.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 934 |
+
"transformer.h.38.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 935 |
+
"transformer.h.38.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 936 |
+
"transformer.h.38.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 937 |
+
"transformer.h.38.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 938 |
+
"transformer.h.38.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 939 |
+
"transformer.h.38.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 940 |
+
"transformer.h.38.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 941 |
+
"transformer.h.38.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 942 |
+
"transformer.h.38.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 943 |
+
"transformer.h.38.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 944 |
+
"transformer.h.38.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 945 |
+
"transformer.h.38.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 946 |
+
"transformer.h.38.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 947 |
+
"transformer.h.38.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 948 |
+
"transformer.h.38.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 949 |
+
"transformer.h.38.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 950 |
+
"transformer.h.38.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 951 |
+
"transformer.h.38.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 952 |
+
"transformer.h.38.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 953 |
+
"transformer.h.38.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 954 |
+
"transformer.h.38.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 955 |
+
"transformer.h.38.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 956 |
+
"transformer.h.38.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 957 |
+
"transformer.h.38.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 958 |
+
"transformer.h.38.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 959 |
+
"transformer.h.38.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 960 |
+
"transformer.h.38.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 961 |
+
"transformer.h.38.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 962 |
+
"transformer.h.38.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 963 |
+
"transformer.h.39.attn.c_attn.bias": "model-00002-of-00002.safetensors",
|
| 964 |
+
"transformer.h.39.attn.c_attn.g_idx": "model-00002-of-00002.safetensors",
|
| 965 |
+
"transformer.h.39.attn.c_attn.qweight": "model-00002-of-00002.safetensors",
|
| 966 |
+
"transformer.h.39.attn.c_attn.qzeros": "model-00002-of-00002.safetensors",
|
| 967 |
+
"transformer.h.39.attn.c_attn.scales": "model-00002-of-00002.safetensors",
|
| 968 |
+
"transformer.h.39.attn.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 969 |
+
"transformer.h.39.attn.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 970 |
+
"transformer.h.39.attn.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 971 |
+
"transformer.h.39.attn.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 972 |
+
"transformer.h.39.attn.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 973 |
+
"transformer.h.39.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 974 |
+
"transformer.h.39.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 975 |
+
"transformer.h.39.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 976 |
+
"transformer.h.39.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 977 |
+
"transformer.h.39.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 978 |
+
"transformer.h.39.mlp.c_fc.g_idx": "model-00002-of-00002.safetensors",
|
| 979 |
+
"transformer.h.39.mlp.c_fc.qweight": "model-00002-of-00002.safetensors",
|
| 980 |
+
"transformer.h.39.mlp.c_fc.qzeros": "model-00002-of-00002.safetensors",
|
| 981 |
+
"transformer.h.39.mlp.c_fc.scales": "model-00002-of-00002.safetensors",
|
| 982 |
+
"transformer.h.39.mlp.c_fc2.bias": "model-00002-of-00002.safetensors",
|
| 983 |
+
"transformer.h.39.mlp.c_fc2.g_idx": "model-00002-of-00002.safetensors",
|
| 984 |
+
"transformer.h.39.mlp.c_fc2.qweight": "model-00002-of-00002.safetensors",
|
| 985 |
+
"transformer.h.39.mlp.c_fc2.qzeros": "model-00002-of-00002.safetensors",
|
| 986 |
+
"transformer.h.39.mlp.c_fc2.scales": "model-00002-of-00002.safetensors",
|
| 987 |
+
"transformer.h.39.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 988 |
+
"transformer.h.39.mlp.c_proj.g_idx": "model-00002-of-00002.safetensors",
|
| 989 |
+
"transformer.h.39.mlp.c_proj.qweight": "model-00002-of-00002.safetensors",
|
| 990 |
+
"transformer.h.39.mlp.c_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 991 |
+
"transformer.h.39.mlp.c_proj.scales": "model-00002-of-00002.safetensors",
|
| 992 |
+
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 993 |
+
"transformer.h.4.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 994 |
+
"transformer.h.4.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 995 |
+
"transformer.h.4.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 996 |
+
"transformer.h.4.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 997 |
+
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 998 |
+
"transformer.h.4.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 999 |
+
"transformer.h.4.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1000 |
+
"transformer.h.4.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1001 |
+
"transformer.h.4.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1002 |
+
"transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 1003 |
+
"transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 1004 |
+
"transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 1005 |
+
"transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 1006 |
+
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 1007 |
+
"transformer.h.4.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 1008 |
+
"transformer.h.4.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 1009 |
+
"transformer.h.4.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 1010 |
+
"transformer.h.4.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 1011 |
+
"transformer.h.4.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 1012 |
+
"transformer.h.4.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 1013 |
+
"transformer.h.4.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 1014 |
+
"transformer.h.4.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 1015 |
+
"transformer.h.4.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 1016 |
+
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1017 |
+
"transformer.h.4.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1018 |
+
"transformer.h.4.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1019 |
+
"transformer.h.4.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1020 |
+
"transformer.h.4.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1021 |
+
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 1022 |
+
"transformer.h.5.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 1023 |
+
"transformer.h.5.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 1024 |
+
"transformer.h.5.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 1025 |
+
"transformer.h.5.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 1026 |
+
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1027 |
+
"transformer.h.5.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1028 |
+
"transformer.h.5.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1029 |
+
"transformer.h.5.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1030 |
+
"transformer.h.5.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1031 |
+
"transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 1032 |
+
"transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 1033 |
+
"transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 1034 |
+
"transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 1035 |
+
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 1036 |
+
"transformer.h.5.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 1037 |
+
"transformer.h.5.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 1038 |
+
"transformer.h.5.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 1039 |
+
"transformer.h.5.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 1040 |
+
"transformer.h.5.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 1041 |
+
"transformer.h.5.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 1042 |
+
"transformer.h.5.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 1043 |
+
"transformer.h.5.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 1044 |
+
"transformer.h.5.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 1045 |
+
"transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1046 |
+
"transformer.h.5.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1047 |
+
"transformer.h.5.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1048 |
+
"transformer.h.5.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1049 |
+
"transformer.h.5.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1050 |
+
"transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 1051 |
+
"transformer.h.6.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 1052 |
+
"transformer.h.6.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 1053 |
+
"transformer.h.6.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 1054 |
+
"transformer.h.6.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 1055 |
+
"transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1056 |
+
"transformer.h.6.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1057 |
+
"transformer.h.6.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1058 |
+
"transformer.h.6.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1059 |
+
"transformer.h.6.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1060 |
+
"transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 1061 |
+
"transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 1062 |
+
"transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 1063 |
+
"transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 1064 |
+
"transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 1065 |
+
"transformer.h.6.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 1066 |
+
"transformer.h.6.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 1067 |
+
"transformer.h.6.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 1068 |
+
"transformer.h.6.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 1069 |
+
"transformer.h.6.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 1070 |
+
"transformer.h.6.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 1071 |
+
"transformer.h.6.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 1072 |
+
"transformer.h.6.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 1073 |
+
"transformer.h.6.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 1074 |
+
"transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1075 |
+
"transformer.h.6.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1076 |
+
"transformer.h.6.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1077 |
+
"transformer.h.6.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1078 |
+
"transformer.h.6.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1079 |
+
"transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 1080 |
+
"transformer.h.7.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 1081 |
+
"transformer.h.7.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 1082 |
+
"transformer.h.7.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 1083 |
+
"transformer.h.7.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 1084 |
+
"transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1085 |
+
"transformer.h.7.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1086 |
+
"transformer.h.7.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1087 |
+
"transformer.h.7.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1088 |
+
"transformer.h.7.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1089 |
+
"transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 1090 |
+
"transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 1091 |
+
"transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 1092 |
+
"transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 1093 |
+
"transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 1094 |
+
"transformer.h.7.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 1095 |
+
"transformer.h.7.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 1096 |
+
"transformer.h.7.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 1097 |
+
"transformer.h.7.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 1098 |
+
"transformer.h.7.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 1099 |
+
"transformer.h.7.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 1100 |
+
"transformer.h.7.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 1101 |
+
"transformer.h.7.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 1102 |
+
"transformer.h.7.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 1103 |
+
"transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1104 |
+
"transformer.h.7.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1105 |
+
"transformer.h.7.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1106 |
+
"transformer.h.7.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1107 |
+
"transformer.h.7.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1108 |
+
"transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 1109 |
+
"transformer.h.8.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 1110 |
+
"transformer.h.8.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 1111 |
+
"transformer.h.8.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 1112 |
+
"transformer.h.8.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 1113 |
+
"transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1114 |
+
"transformer.h.8.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1115 |
+
"transformer.h.8.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1116 |
+
"transformer.h.8.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1117 |
+
"transformer.h.8.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1118 |
+
"transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 1119 |
+
"transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 1120 |
+
"transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 1121 |
+
"transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 1122 |
+
"transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 1123 |
+
"transformer.h.8.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 1124 |
+
"transformer.h.8.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 1125 |
+
"transformer.h.8.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 1126 |
+
"transformer.h.8.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 1127 |
+
"transformer.h.8.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 1128 |
+
"transformer.h.8.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 1129 |
+
"transformer.h.8.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 1130 |
+
"transformer.h.8.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 1131 |
+
"transformer.h.8.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 1132 |
+
"transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1133 |
+
"transformer.h.8.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1134 |
+
"transformer.h.8.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1135 |
+
"transformer.h.8.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1136 |
+
"transformer.h.8.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1137 |
+
"transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 1138 |
+
"transformer.h.9.attn.c_attn.g_idx": "model-00001-of-00002.safetensors",
|
| 1139 |
+
"transformer.h.9.attn.c_attn.qweight": "model-00001-of-00002.safetensors",
|
| 1140 |
+
"transformer.h.9.attn.c_attn.qzeros": "model-00001-of-00002.safetensors",
|
| 1141 |
+
"transformer.h.9.attn.c_attn.scales": "model-00001-of-00002.safetensors",
|
| 1142 |
+
"transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1143 |
+
"transformer.h.9.attn.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1144 |
+
"transformer.h.9.attn.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1145 |
+
"transformer.h.9.attn.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1146 |
+
"transformer.h.9.attn.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1147 |
+
"transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 1148 |
+
"transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 1149 |
+
"transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 1150 |
+
"transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 1151 |
+
"transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 1152 |
+
"transformer.h.9.mlp.c_fc.g_idx": "model-00001-of-00002.safetensors",
|
| 1153 |
+
"transformer.h.9.mlp.c_fc.qweight": "model-00001-of-00002.safetensors",
|
| 1154 |
+
"transformer.h.9.mlp.c_fc.qzeros": "model-00001-of-00002.safetensors",
|
| 1155 |
+
"transformer.h.9.mlp.c_fc.scales": "model-00001-of-00002.safetensors",
|
| 1156 |
+
"transformer.h.9.mlp.c_fc2.bias": "model-00001-of-00002.safetensors",
|
| 1157 |
+
"transformer.h.9.mlp.c_fc2.g_idx": "model-00001-of-00002.safetensors",
|
| 1158 |
+
"transformer.h.9.mlp.c_fc2.qweight": "model-00001-of-00002.safetensors",
|
| 1159 |
+
"transformer.h.9.mlp.c_fc2.qzeros": "model-00001-of-00002.safetensors",
|
| 1160 |
+
"transformer.h.9.mlp.c_fc2.scales": "model-00001-of-00002.safetensors",
|
| 1161 |
+
"transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 1162 |
+
"transformer.h.9.mlp.c_proj.g_idx": "model-00001-of-00002.safetensors",
|
| 1163 |
+
"transformer.h.9.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 1164 |
+
"transformer.h.9.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 1165 |
+
"transformer.h.9.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 1166 |
+
"transformer.ln_f.bias": "model-00002-of-00002.safetensors",
|
| 1167 |
+
"transformer.ln_f.weight": "model-00002-of-00002.safetensors",
|
| 1168 |
+
"transformer.relative_pe.slopes": "model-00002-of-00002.safetensors",
|
| 1169 |
+
"transformer.wte.weight": "model-00001-of-00002.safetensors"
|
| 1170 |
+
}
|
| 1171 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<|endoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
+
"bos_token": "<|endoftext|>",
|
| 13 |
+
"clean_up_tokenization_spaces": true,
|
| 14 |
+
"eos_token": "<|endoftext|>",
|
| 15 |
+
"model_max_length": 2048,
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 18 |
+
"unk_token": "<|endoftext|>"
|
| 19 |
+
}
|