Downloads · 30 days
0
llm-jp-3-13b-ichikara_all
msfm/llm-jp-3-13b-ichikara_all
llm-jp-3-13b-ichikara_all is a machine learning model from msfm. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: msfm - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Access
Public
Updated Dec 20, 2024
Repo size
501 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors501 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Dec 2, 2024
- Updated
- Dec 20, 2024
- SHA
- af77d8f0
Base models
Model card
From the Hugging Face model README
Uploaded model
- Developed by: msfm
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Example
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name="msfm/llm-jp-3-13b-ichikara_all",
dtype=dtype,
load_in_4bit=True,
trust_remote_code=True,
)
FastLanguageModel.for_inference(model)
input = "野球選手が今シーズン活躍するために取り組むべき5つのことを教えてください。"
prompt = f"""### 指示\n{input}\n### 回答\n"""
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens = 2048, use_cache = True, do_sample=False, repetition_penalty=1.2)
prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
- Library
- transformers
- License
- apache-2.0
- Languages
- en
- Created
- Dec 2, 2024
- Updated
- Dec 20, 2024