Upload folder using huggingface_hub
Browse files- README.md +69 -0
- config.json +34 -0
- mergekit_moe_config.yml +18 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- frankenmoe
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- vihangd/DopeyTinyLlama-1.1B-v1
|
10 |
+
- phanerozoic/Tiny-Pirate-1.1b-v0.1
|
11 |
+
- Tensoic/TinyLlama-1.1B-3T-openhermes
|
12 |
+
base_model:
|
13 |
+
- vihangd/DopeyTinyLlama-1.1B-v1
|
14 |
+
- phanerozoic/Tiny-Pirate-1.1b-v0.1
|
15 |
+
- Tensoic/TinyLlama-1.1B-3T-openhermes
|
16 |
+
---
|
17 |
+
|
18 |
+
# Tinyllama-moe1
|
19 |
+
|
20 |
+
Tinyllama-moe1 is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
21 |
+
* [vihangd/DopeyTinyLlama-1.1B-v1](https://huggingface.co/vihangd/DopeyTinyLlama-1.1B-v1)
|
22 |
+
* [phanerozoic/Tiny-Pirate-1.1b-v0.1](https://huggingface.co/phanerozoic/Tiny-Pirate-1.1b-v0.1)
|
23 |
+
* [Tensoic/TinyLlama-1.1B-3T-openhermes](https://huggingface.co/Tensoic/TinyLlama-1.1B-3T-openhermes)
|
24 |
+
|
25 |
+
## 🧩 Configuration
|
26 |
+
|
27 |
+
```yaml
|
28 |
+
base_model: vihangd/DopeyTinyLlama-1.1B-v1
|
29 |
+
experts:
|
30 |
+
- source_model: vihangd/DopeyTinyLlama-1.1B-v1
|
31 |
+
positive_prompts:
|
32 |
+
- "chat"
|
33 |
+
- "assistant"
|
34 |
+
- "explain"
|
35 |
+
- source_model: phanerozoic/Tiny-Pirate-1.1b-v0.1
|
36 |
+
positive_prompts:
|
37 |
+
- "storywriting"
|
38 |
+
- "scene"
|
39 |
+
- "story"
|
40 |
+
- source_model: Tensoic/TinyLlama-1.1B-3T-openhermes
|
41 |
+
positive_prompts:
|
42 |
+
- "reason"
|
43 |
+
- "instruct"
|
44 |
+
- "count"
|
45 |
+
```
|
46 |
+
|
47 |
+
## 💻 Usage
|
48 |
+
|
49 |
+
```python
|
50 |
+
!pip install -qU transformers bitsandbytes accelerate
|
51 |
+
|
52 |
+
from transformers import AutoTokenizer
|
53 |
+
import transformers
|
54 |
+
import torch
|
55 |
+
|
56 |
+
model = "aipib/Tinyllama-moe1"
|
57 |
+
|
58 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
59 |
+
pipeline = transformers.pipeline(
|
60 |
+
"text-generation",
|
61 |
+
model=model,
|
62 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
63 |
+
)
|
64 |
+
|
65 |
+
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
|
66 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
67 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
68 |
+
print(outputs[0]["generated_text"])
|
69 |
+
```
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vihangd/DopeyTinyLlama-1.1B-v1",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 22,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"num_local_experts": 3,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"router_aux_loss_coef": 0.001,
|
27 |
+
"router_jitter_noise": 0.0,
|
28 |
+
"sliding_window": null,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float16",
|
31 |
+
"transformers_version": "4.40.1",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 32000
|
34 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: vihangd/DopeyTinyLlama-1.1B-v1
|
3 |
+
experts:
|
4 |
+
- source_model: vihangd/DopeyTinyLlama-1.1B-v1
|
5 |
+
positive_prompts:
|
6 |
+
- "chat"
|
7 |
+
- "assistant"
|
8 |
+
- "explain"
|
9 |
+
- source_model: phanerozoic/Tiny-Pirate-1.1b-v0.1
|
10 |
+
positive_prompts:
|
11 |
+
- "storywriting"
|
12 |
+
- "scene"
|
13 |
+
- "story"
|
14 |
+
- source_model: Tensoic/TinyLlama-1.1B-3T-openhermes
|
15 |
+
positive_prompts:
|
16 |
+
- "reason"
|
17 |
+
- "instruct"
|
18 |
+
- "count"
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10f5187968150abcaa700e9bd121fad523b08aeeb751700384f2f3fececbd504
|
3 |
+
size 1992400992
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2557acdba856a9bb10e3f1882da5daa73aebe2df09bb74d05493594797da227f
|
3 |
+
size 1983916864
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac600d23f8900023c85f6a1b6fa3190ce559b2c5e94af8015ce71fad505ce618
|
3 |
+
size 1269157440
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.norm.weight": "model-00001-of-00003.safetensors", "lm_head.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00003.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00003.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 2048,
|
36 |
+
"pad_token": "<s>",
|
37 |
+
"padding_side": "left",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|