---
inference: false
---
# weblab-10b-instruction-sft-GPTQ 

original model [weblab-10b-instruction-sft](https://huggingface.co/matsuo-lab/weblab-10b-instruction-sft)

This is 4bit GPTQ Version.

The size is smaller and the execution speed is faster, but the inference performance may be a little worse.


### sample code
At least one GPU is currently required due to a limitation of the Accelerate library.  

```
pip install auto-gptq
```

```
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

quantized_model_dir = "dahara1/weblab-10b-instruction-sft-GPTQ"
model_basename = "gptq_model-4bit-128g"

tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)

model = AutoGPTQForCausalLM.from_quantized(
        quantized_model_dir,
        model_basename=model_basename,
        use_safetensors=True,
        device="cuda:0")

prompt = "スタジオジブリの作品を５つ教えてください"
prompt_template = f"### 指示: {prompt}\n\n### 応答:"

tokens = tokenizer(prompt_template, return_tensors="pt").to("cuda:0").input_ids
output = model.generate(input_ids=tokens, max_new_tokens=100, do_sample=True, temperature=0.8)
print(tokenizer.decode(output[0]))
```

### See Also
https://github.com/PanQiWei/AutoGPTQ/blob/main/docs/tutorial/01-Quick-Start.md


### Benchmark

The results below are preliminary. The blank part is under measurement.

* **Japanese benchmark**

    - *We used [Stability-AI/lm-evaluation-harness](https://github.com/Stability-AI/lm-evaluation-harness/tree/jp-stable) + gptq patch for evaluation.*
    - *The 4-task average accuracy is based on results of JCommonsenseQA-1.1, JNLI-1.1, MARC-ja-1.1, and JSQuAD-1.1.*
    - *model loading is performed with gptq_use_triton=True, and evaluation is performed with template version 0.3 using the few-shot in-context learning.*
    - *The number of few-shots is 3,3,3,2.*
   
    | Model | Average | JCommonsenseQA | JNLI | MARC-ja | JSQuAD |
    | :-- | :-- | :-- | :-- | :-- | :-- |
    | weblab-10b-instruction-sft | 78.78 | 74.35 | 65.65 | 96.06 | 79.04 |
    | weblab-10b | 66.38 | 65.86 | 54.19 | 84.49 | 60.98 |
    | *weblab-10b-instruction-sft-GPTQ* | - | 74.53 | 41.70 | - | 72.69 |