Instructions to use ce-lery/mistral-300m-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ce-lery/mistral-300m-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("ce-lery/mistral-300m-base")
model = PeftModel.from_pretrained(base_model, "ce-lery/mistral-300m-sft")

Transformers

How to use ce-lery/mistral-300m-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ce-lery/mistral-300m-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ce-lery/mistral-300m-sft", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ce-lery/mistral-300m-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ce-lery/mistral-300m-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ce-lery/mistral-300m-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ce-lery/mistral-300m-sft

SGLang

How to use ce-lery/mistral-300m-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ce-lery/mistral-300m-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ce-lery/mistral-300m-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ce-lery/mistral-300m-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ce-lery/mistral-300m-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ce-lery/mistral-300m-sft with Docker Model Runner:
```
docker model run hf.co/ce-lery/mistral-300m-sft
```

mistral-300m-sft

Overview

Welcome to my model card!

This Model feature is ...

LoRA fine-tuning model of ce-lery/mistral-300m-base
Use of Mistral 300M

Yukkuri shite ittene!

How to use the model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

def inference(model_path:str, device: str = "cuda", prompt:str = ""):

    if (device != "cuda" and device != "cpu"):
        device = "cpu"
    if not torch.cuda.is_available():
        device = "cpu"
    print("device:", device)

    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(model_path,trust_remote_code=True).to(device)

    messages = [{"role": "user", "content": prompt}]
    tokenized_chat = tokenizer.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_tensors="pt"
    )
    # token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
    # print("token_ids:",token_ids)

    with torch.no_grad():
        generated_tokens = model.generate(
            tokenized_chat.to("cuda"), 
            use_cache=True, 
            early_stopping=False,
            max_new_tokens=1024,
            top_p=0.95,
            top_k=50,
            temperature=0.2,
            do_sample=True,
            no_repeat_ngram_size=2,
            num_beams=3,
        )
    generated_text = tokenizer.decode(generated_tokens[0])
    print(generated_text.replace(tokenizer.eos_token, "\n"))

prompt = "こんにちは！"
inference("ce-lery/mistral-300m-sft", "cuda", prompt)
#<s>User:こんにちは！
#<s>Assistant:おはようございます。私はオープンアシスタントです。あなたの質問に答えたり、あなたの質問にお答えします。何かお手伝いできることがあれば、遠慮なく聞いてください。

prompt = "自動車を運転する際に必要なものは？"
inference("ce-lery/mistral-300m-sft", "cuda", prompt)
#<s>User:自動車を運転する際に必要なものは？
#<s>Assistant:運転に必要なすべての道具と装備をそろえるには、いくつかのステップを踏む必要があります。以下はそのステップのステップ・バイ・ステップです。
#
#1.  運転する場所の道路状況を調べる。これは、道路の状況を把握するのに役立ちます。また、交通量や道路の混雑状況など、さまざまな要因を考慮することも重要です。例えば、高速道路での運転は、渋滞や事故のリスクが高まるため、避けるべきである。さらに、車間距離を十分にとって、周囲の状況に注意を払い、危険を回避し、安全を確保するために十分な注意を払うことも重要である。更に、安全な運転をするために、ブレーキとアクセルの踏み間違いや、アクセルとブレーキを間違えるなどのミスを犯さないよう、注意深く運転することも必要です。

prompt = "日本の首都は？"
inference("ce-lery/mistral-300m-sft", "cuda", prompt)
#<s>User:日本の首都は？
#<s>Assistant:東京は日本で最も人口の多い都市であり、人口密度の高い都市です。

Receipe

If you want to restruct this model, you can refer this Github repository.
And the manual of this repository is here. Please refer it.

If you find my mistake,error,...etc, please create issue. If you create pulreqest, I'm very happy!

Training procedure

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4
PEFT 0.17.1

Downloads last month: 3

Model tree for ce-lery/mistral-300m-sft

Base model

ce-lery/mistral-300m-base

Adapter

(1)

this model