|
--- |
|
license: llama3 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- not-for-all-audiences |
|
base_model: |
|
- Hastagaras/anjrit |
|
- Hastagaras/anying |
|
model-index: |
|
- name: Anjir-8B-L3 |
|
results: |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: AI2 Reasoning Challenge (25-Shot) |
|
type: ai2_arc |
|
config: ARC-Challenge |
|
split: test |
|
args: |
|
num_few_shot: 25 |
|
metrics: |
|
- type: acc_norm |
|
value: 63.57 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Anjir-8B-L3 |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: HellaSwag (10-Shot) |
|
type: hellaswag |
|
split: validation |
|
args: |
|
num_few_shot: 10 |
|
metrics: |
|
- type: acc_norm |
|
value: 84.15 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Anjir-8B-L3 |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: MMLU (5-Shot) |
|
type: cais/mmlu |
|
config: all |
|
split: test |
|
args: |
|
num_few_shot: 5 |
|
metrics: |
|
- type: acc |
|
value: 67.67 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Anjir-8B-L3 |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: TruthfulQA (0-shot) |
|
type: truthful_qa |
|
config: multiple_choice |
|
split: validation |
|
args: |
|
num_few_shot: 0 |
|
metrics: |
|
- type: mc2 |
|
value: 52.67 |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Anjir-8B-L3 |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: Winogrande (5-shot) |
|
type: winogrande |
|
config: winogrande_xl |
|
split: validation |
|
args: |
|
num_few_shot: 5 |
|
metrics: |
|
- type: acc |
|
value: 78.61 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Anjir-8B-L3 |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: GSM8k (5-shot) |
|
type: gsm8k |
|
config: main |
|
split: test |
|
args: |
|
num_few_shot: 5 |
|
metrics: |
|
- type: acc |
|
value: 67.78 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Anjir-8B-L3 |
|
name: Open LLM Leaderboard |
|
--- |
|
# ⚡ExLlamaV2 quant of : [Anjir-8B-L3](https://huggingface.co/Hastagaras/Anjir-8B-L3) |
|
> [!note] |
|
> ➡️ **Exl2 version :** [0.1.1](https://github.com/turboderp/exllamav2/releases/tag/v0.1.1)<br/> |
|
> ➡️ **Cal. dataset :** Default.<br/> |
|
> 📄 <a href="https://huggingface.co/Meggido/Anjir-8B-L3-6.5bpw-h8-exl2/resolve/main/measurement.json" download>Measurement.json</a> file. |
|
|
|
# ANJIRRR |
|
|
|
This model aims to achieve the human-like responses of the [Halu Blackroot](https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot), the no refusal tendencies of the [Halu OAS](https://huggingface.co/Hastagaras/Halu-OAS-8B-Llama3), and the smartness of the [Standard Halu](https://huggingface.co/Hastagaras/Halu-8B-Llama3-v0.3). |
|
|
|
GGUF: [**STATIC**](https://huggingface.co/mradermacher/Anjir-8B-L3-GGUF)/[**IMATRIX**](https://huggingface.co/mradermacher/Anjir-8B-L3-i1-GGUF) made available by [mradermacher](https://huggingface.co/mradermacher) |
|
|
|
<div align="left"> |
|
<img src="https://huggingface.co/Hastagaras/Anjir-8B-L3/resolve/main/anjir.png" width="500"/> |
|
</div> |
|
|
|
**Model Details:** |
|
|
|
* **Anjrit:** This model is similar to my [Halu Blackroot](https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot) model, but instead of using the standard version, this model uses the OAS version. |
|
|
|
* **Anying:** This model is also similar to the Halu Blackroot, but instead of using the model stock, I merged the Blackroot lora manually with a very low alpha. |
|
|
|
Both models have downsides. The Anjrit model **lacks coherency**, while the Anying model lacks a **human-like responses**. |
|
|
|
**I decided to merge both models with the following method:** |
|
|
|
1. First, I compared the response from each layer of both models using the baukit notebook. |
|
|
|
2. After comparing both, it seems that around the bottom layer, the Anjrit model is better, perhaps because it is unhinged. |
|
|
|
3. From the bottom to the middle layer, the Anjrit is still better, but the Anying seems smarter. |
|
|
|
4. At the middle layer, both seem equal, but again, the Anjrit is unhinged, so I prefer this one. |
|
|
|
5. From the middle to the top layer, the Anying is better. It is smarter, and the response is more structured. |
|
|
|
6. The top layer of the Anjrit model is better since the model itself is orthogonalized, so I prefer this one. |
|
|
|
7. Then I performed slerp with the following configuration. I don't know if this is really how the slerp merge works, so let's just say this is an **experimental merge**. Maybe I will try the other merge methods for future experiments |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: Hastagaras/anjrit |
|
- model: Hastagaras/anying |
|
merge_method: slerp |
|
base_model: Hastagaras/anjrit |
|
dtype: bfloat16 |
|
parameters: |
|
t: [0.12, 0.17, 0.29, 0.44, 0.26] |
|
|
|
``` |
|
|
|
--- |
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Hastagaras__Anjir-8B-L3) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |69.07| |
|
|AI2 Reasoning Challenge (25-Shot)|63.57| |
|
|HellaSwag (10-Shot) |84.15| |
|
|MMLU (5-Shot) |67.67| |
|
|TruthfulQA (0-shot) |52.67| |
|
|Winogrande (5-shot) |78.61| |
|
|GSM8k (5-shot) |67.78| |
|
|
|
|