Instructions to use Ja-ck/Mistral-instruct-IPO-Y24-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ja-ck/Mistral-instruct-IPO-Y24-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Ja-ck/Mistral-instruct-IPO-Y24-v1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ja-ck/Mistral-instruct-IPO-Y24-v1")
model = AutoModelForCausalLM.from_pretrained("Ja-ck/Mistral-instruct-IPO-Y24-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ja-ck/Mistral-instruct-IPO-Y24-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ja-ck/Mistral-instruct-IPO-Y24-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ja-ck/Mistral-instruct-IPO-Y24-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ja-ck/Mistral-instruct-IPO-Y24-v1

SGLang

How to use Ja-ck/Mistral-instruct-IPO-Y24-v1 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 "Ja-ck/Mistral-instruct-IPO-Y24-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ja-ck/Mistral-instruct-IPO-Y24-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Ja-ck/Mistral-instruct-IPO-Y24-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ja-ck/Mistral-instruct-IPO-Y24-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ja-ck/Mistral-instruct-IPO-Y24-v1 with Docker Model Runner:
```
docker model run hf.co/Ja-ck/Mistral-instruct-IPO-Y24-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Prompt Tempalte

It follows Alpaca format.

### 질문: {instruction}
### 답변: {output}

Implementation Code

import troch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.fron_pretrained("Ja3ck/Mistral-instruct-IPO-Y24-v1", return_dict=True, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Ja3ck/Mistral-instruct-IPO-Y24-v1", use_fast=True)
tokenizer.pad_token = tokenizer.unk_token
tokenizer.pad_token_id = tokenizer.unk_token_id
tokenizer.padding_side = "left"

def gen(x):
  x_ = f"### 질문: {x.strip()} ### 답변: "
  inputs = tokenizer(x_, return_tensor='pt')
  input_ids = inputs['input_ids'].cuda()
  generation_output = model.generate(
      pad_token_id = tokenizer.pad_token_id,
      temperature=0.1,
      top_p=1,
      top_k=50,
      num_beams=1,
      repetition_penalty=1.13,
      do_sample=True,
    ),
    return_dict_in_generate=True,
    output_scores=True,
    max_new_tokens=1024
  )
  for seq in generation_output.sequences:
    output = tokenizer.decode(seq)
    print(output.split("### 답변: ")[1].strip())

gen("안녕하세요?")

Downloads last month: 22

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Ja-ck/Mistral-instruct-IPO-Y24-v1

Quantizations

1 model