Instructions to use EmbeddedLLM/Mistral-7B-Merge-14-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="EmbeddedLLM/Mistral-7B-Merge-14-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/Mistral-7B-Merge-14-v0.1")
model = AutoModelForCausalLM.from_pretrained("EmbeddedLLM/Mistral-7B-Merge-14-v0.1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/Mistral-7B-Merge-14-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/Mistral-7B-Merge-14-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1

SGLang

How to use EmbeddedLLM/Mistral-7B-Merge-14-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 "EmbeddedLLM/Mistral-7B-Merge-14-v0.1" \
    --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": "EmbeddedLLM/Mistral-7B-Merge-14-v0.1",
		"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 "EmbeddedLLM/Mistral-7B-Merge-14-v0.1" \
        --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": "EmbeddedLLM/Mistral-7B-Merge-14-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EmbeddedLLM/Mistral-7B-Merge-14-v0.1 with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1
```

Mistral-7B-Merge-14-v0.1

Commit History

Adding Evaluation Results

31c4c33
verified

leaderboard-pr-bot commited on Mar 4, 2024

Update base model metadata

5441a9f
verified

thesunday commited on Jan 20, 2024

Add base_model to link all the parent models (#1)

6d3d017
verified

thesunday

mlabonne commited on Jan 20, 2024

Update README.md

5ba39f3

thesunday commited on Jan 3, 2024

Update README.md

3ddae31

thesunday commited on Dec 19, 2023

Update README.md

7f04647

thesunday commited on Dec 19, 2023

Update README.md

4af63c9

thesunday commited on Dec 19, 2023

Update model card

0e124af

thesunday commited on Dec 18, 2023

Add model files

a1d03f2

Jia Huei Tan commited on Dec 18, 2023

initial commit

bc9b480

thesunday commited on Dec 18, 2023

Commit History

Adding Evaluation Results 31c4c33 verified

Update base model metadata 5441a9f verified

Add base_model to link all the parent models (#1) 6d3d017 verified

Update README.md 5ba39f3

Update README.md 3ddae31

Update README.md 7f04647

Update README.md 4af63c9

Update model card 0e124af

Add model files a1d03f2

initial commit bc9b480

Adding Evaluation Results

31c4c33
verified

Update base model metadata

5441a9f
verified

Add base_model to link all the parent models (#1)

6d3d017
verified

Update README.md

5ba39f3

Update README.md

3ddae31

Update README.md

7f04647

Update README.md

4af63c9

Update model card

0e124af

Add model files

a1d03f2

initial commit

bc9b480