Hugging Face's logo

1kbooks
/
llm-jp-3-13b-finetuned-ver2

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
llm-jp-3-13b-finetuned-ver2 / README.md
1kbooks's picture
1kbooks
Update README.md
b4022cd verified
preview code
|
raw
history blame contribute delete
3.89 kB
metadata
library_name: transformers
license: apache-2.0
base_model:
  - llm-jp/llm-jp-3-13b
pipeline_tag: text-generation

Model Card for Model ID

llm-jp-3-13bをichikaraデータセットでファインチューニングしたモデル

Model Details

Model Description

NEFTuneによりファインチューニングを実行

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use 

model_id = "1kbooks/llm-jp-3-13b-finetuned-ver2"
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4", 
    bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    quantization_config=bnb_config,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

input  = "ここに指示を入力"
with torch.no_grad():
  prompt = f"""### 指示\n{input}\n### 回答\n"""

  inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
  attention_mask = torch.ones_like(tokenized_input)

  outputs = model.generate(
      tokenized_input,
      attention_mask=attention_mask,
      max_new_tokens = 512, 
      use_cache = True, 
      do_sample=False, 
      repetition_penalty=1.2,
      pad_token_id=tokenizer.eos_token_id
  )
  prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]

print(prediction)

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

  • ichikara dataset

Training Procedure

  • NEFTune