Instructions to use BaiqingL/mistral-7b-dolly with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BaiqingL/mistral-7b-dolly with Transformers:

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

pipe = pipeline("text-generation", model="BaiqingL/mistral-7b-dolly")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BaiqingL/mistral-7b-dolly")
model = AutoModelForCausalLM.from_pretrained("BaiqingL/mistral-7b-dolly")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BaiqingL/mistral-7b-dolly with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BaiqingL/mistral-7b-dolly"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BaiqingL/mistral-7b-dolly",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BaiqingL/mistral-7b-dolly

SGLang

How to use BaiqingL/mistral-7b-dolly 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 "BaiqingL/mistral-7b-dolly" \
    --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": "BaiqingL/mistral-7b-dolly",
		"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 "BaiqingL/mistral-7b-dolly" \
        --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": "BaiqingL/mistral-7b-dolly",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BaiqingL/mistral-7b-dolly with Docker Model Runner:
```
docker model run hf.co/BaiqingL/mistral-7b-dolly
```

Run history:

        train/epoch ▁▂▂▃▃▄▄▅▅▆▆▇▇██
  train/global_step ▁▂▂▃▃▄▄▅▅▆▆▇▇██
train/learning_rate ██▇▇▆▅▅▄▃▂▂▁▁▁
         train/loss █▇▇▇▇▄▄▃▃▃▁▁▁▁

Run summary:
  total_flos 1.2561212617261056e+16
  train/epoch 2.95288
  train/global_step 141
  train/learning_rate 0.0
  train/loss 0.3328
  train_loss 0.86429
  train_runtime 684.2978
  train_samples_per_second 1.675
  train_steps_per_second 0.206

Downloads last month: 9

Safetensors

Model size

7B params

Tensor type

F32