Instructions to use phospho-app/mistral_7b_V0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use phospho-app/mistral_7b_V0.1 with Transformers:

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

pipe = pipeline("text-generation", model="phospho-app/mistral_7b_V0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("phospho-app/mistral_7b_V0.1")
model = AutoModelForCausalLM.from_pretrained("phospho-app/mistral_7b_V0.1")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use phospho-app/mistral_7b_V0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "phospho-app/mistral_7b_V0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "phospho-app/mistral_7b_V0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/phospho-app/mistral_7b_V0.1

SGLang

How to use phospho-app/mistral_7b_V0.1 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 "phospho-app/mistral_7b_V0.1" \
    --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": "phospho-app/mistral_7b_V0.1",
		"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 "phospho-app/mistral_7b_V0.1" \
        --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": "phospho-app/mistral_7b_V0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use phospho-app/mistral_7b_V0.1 with Docker Model Runner:
```
docker model run hf.co/phospho-app/mistral_7b_V0.1
```

Mistral 7B V0.1

Implementation of Mistral 7B model by the phospho team. You can test it directly in the HuggingFace space.

Use in transformers

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer, pipeline, TextStreamer

tokenizer = LlamaTokenizer.from_pretrained("phospho-app/mistral_7b_V0.1")
model = LlamaForCausalLM.from_pretrained("phospho-app/mistral_7b_V0.1", torch_dtype=torch.bfloat16)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

Downloads last month: 9