Instructions to use dystrio/Mistral-7B-Instruct-v0.3-sculpt-default with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dystrio/Mistral-7B-Instruct-v0.3-sculpt-default with Transformers:

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

pipe = pipeline("text-generation", model="dystrio/Mistral-7B-Instruct-v0.3-sculpt-default")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dystrio/Mistral-7B-Instruct-v0.3-sculpt-default")
model = AutoModelForCausalLM.from_pretrained("dystrio/Mistral-7B-Instruct-v0.3-sculpt-default", device_map="auto")
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 Settings

vLLM

How to use dystrio/Mistral-7B-Instruct-v0.3-sculpt-default with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dystrio/Mistral-7B-Instruct-v0.3-sculpt-default"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dystrio/Mistral-7B-Instruct-v0.3-sculpt-default",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dystrio/Mistral-7B-Instruct-v0.3-sculpt-default

SGLang

How to use dystrio/Mistral-7B-Instruct-v0.3-sculpt-default 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 "dystrio/Mistral-7B-Instruct-v0.3-sculpt-default" \
    --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": "dystrio/Mistral-7B-Instruct-v0.3-sculpt-default",
		"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 "dystrio/Mistral-7B-Instruct-v0.3-sculpt-default" \
        --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": "dystrio/Mistral-7B-Instruct-v0.3-sculpt-default",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dystrio/Mistral-7B-Instruct-v0.3-sculpt-default with Docker Model Runner:
```
docker model run hf.co/dystrio/Mistral-7B-Instruct-v0.3-sculpt-default
```

dystrio commited on Mar 16

Commit

11bb3cf

verified ·

1 Parent(s): 0af8b23

add downstream benchmarks (ARC-C, HellaSwag, MMLU, TruthfulQA)

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -137,3 +137,14 @@ Dystrio Sculpt compiles transformer models into smaller, faster variants. Output
   url={https://huggingface.co/dystrio}
 }
 ```

   url={https://huggingface.co/dystrio}
 }
 ```
+## Downstream Benchmarks (lm-eval)
+Evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness) on A100-80GB, bf16, zero-shot.
+| Benchmark | Baseline | This Model | Delta |
+|-----------|:--------:|:----------:|:-----:|
+| ARC-Challenge | 0.5794 | 0.4974 | -0.0820 |
+| HellaSwag | 0.6573 | 0.5970 | -0.0603 |
+| MMLU | 0.5975 | 0.4959 | -0.1016 |
+| TruthfulQA MC2 | 0.5939 | 0.5378 | -0.0561 |