Instructions to use Moses25/Mistral-7B-Instruct-V0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Moses25/Mistral-7B-Instruct-V0.3 with Transformers:

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

pipe = pipeline("text-generation", model="Moses25/Mistral-7B-Instruct-V0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Moses25/Mistral-7B-Instruct-V0.3")
model = AutoModelForCausalLM.from_pretrained("Moses25/Mistral-7B-Instruct-V0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Moses25/Mistral-7B-Instruct-V0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Moses25/Mistral-7B-Instruct-V0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Moses25/Mistral-7B-Instruct-V0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Moses25/Mistral-7B-Instruct-V0.3

SGLang

How to use Moses25/Mistral-7B-Instruct-V0.3 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 "Moses25/Mistral-7B-Instruct-V0.3" \
    --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": "Moses25/Mistral-7B-Instruct-V0.3",
		"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 "Moses25/Mistral-7B-Instruct-V0.3" \
        --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": "Moses25/Mistral-7B-Instruct-V0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Moses25/Mistral-7B-Instruct-V0.3 with Docker Model Runner:
```
docker model run hf.co/Moses25/Mistral-7B-Instruct-V0.3
```

This model is trained from Mistral-7B-Instruct-V0.2 with 90% chinese dataset and 10% english dataset

github Web-UI

from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer,AutoTokenizer,AutoModelForCausalLM,MistralForCausalLM
import torch

model_id=Mistral-7B-Instruct-v0.3

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype=torch.bfloat16,device_map="auto",)
prompt = "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant.Help humman as much as you can.\n<</SYS>>\n\n{instruction} [/INST]"
text = prompt.format_map({"instruction":"你好，最近干嘛呢"})

def predict(content_prompt):
    inputs = tokenizer(content_prompt,return_tensors="pt",add_special_tokens=True)
    input_ids = inputs["input_ids"].to("cuda:0")
    # print(f"input length:{len(input_ids[0])}")
    with torch.no_grad():
        generation_output = model.generate(
                    input_ids=input_ids,
                    #generation_config=generation_config,
                    return_dict_in_generate=True,
                    output_scores=True,
                    max_new_tokens=2048,
                    top_p=0.9,
                    num_beams=1,
                    do_sample=True,
                    repetition_penalty=1.0,
                    eos_token_id=tokenizer.eos_token_id,
                    pad_token_id=tokenizer.pad_token_id,
                )
        s = generation_output.sequences[0]
        output = tokenizer.decode(s,skip_special_tokens=True)
        output1 = output.split("[/INST]")[-1].strip()
        # print(output1)
    return output1

predict(text)
output：你好！作为一个大型语言模型，我一直在学习和提高自己的能力。最近，我一直在努力学习新知识、改进算法，以便更好地回答用户的问题并提供帮助。同时，我也会定期接受人工智能专家的指导和评估，以确保我的表现不断提升。希望这些信息对你有所帮助！

Downloads last month: 11

Safetensors

Model size

7B params

Tensor type

F16