Instructions to use Undi95/Mistral-11B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/Mistral-11B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/Mistral-11B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/Mistral-11B-v0.1")
model = AutoModelForCausalLM.from_pretrained("Undi95/Mistral-11B-v0.1")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/Mistral-11B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/Mistral-11B-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": "Undi95/Mistral-11B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/Mistral-11B-v0.1

SGLang

How to use Undi95/Mistral-11B-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 "Undi95/Mistral-11B-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": "Undi95/Mistral-11B-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 "Undi95/Mistral-11B-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": "Undi95/Mistral-11B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/Mistral-11B-v0.1 with Docker Model Runner:
```
docker model run hf.co/Undi95/Mistral-11B-v0.1
```

This is Mistral, but in 11B.

I took layers of the original Mistral-7B, and duplicated some layer, this is the first frankeinstein method that I found "acceptable" to expend Mistral.

It seems that the first 8 layers of the model is very important, having duplicate of those layers in the model make me think it confuse the model.

UPDATE: Forced mergekit to output bfloat16 file, should be the same thing, but since the base model is bfloat16, wanted it to stay bf16 like the OG model. Even if it was written bfloat16 in the config file earlier, it was float16.

Description

This repo contains fp16 files of Mistral-11B-v0.1.

Model used

Mistral-7B-v0.1

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

The secret sauce

slices:
  - sources:
    - model: mistralai/Mistral-7B-v0.1
      layer_range: [0, 24]
  - sources:
    - model: mistralai/Mistral-7B-v0.1
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

Special thanks to Sushi.

If you want to support me, you can here.

Downloads last month: 226

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for Undi95/Mistral-11B-v0.1

Merges

1 model