Instructions to use NousResearch/Yarn-Mistral-7b-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Yarn-Mistral-7b-128k with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Yarn-Mistral-7b-128k", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Yarn-Mistral-7b-128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("NousResearch/Yarn-Mistral-7b-128k", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Yarn-Mistral-7b-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Yarn-Mistral-7b-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Yarn-Mistral-7b-128k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NousResearch/Yarn-Mistral-7b-128k

SGLang

How to use NousResearch/Yarn-Mistral-7b-128k 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 "NousResearch/Yarn-Mistral-7b-128k" \
    --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": "NousResearch/Yarn-Mistral-7b-128k",
		"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 "NousResearch/Yarn-Mistral-7b-128k" \
        --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": "NousResearch/Yarn-Mistral-7b-128k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NousResearch/Yarn-Mistral-7b-128k with Docker Model Runner:
```
docker model run hf.co/NousResearch/Yarn-Mistral-7b-128k
```

Using this model with Vllm

#10

by haltux - opened Nov 8, 2023

Discussion

haltux

Nov 8, 2023

Hello,

I could make the model work directly in Python with the example code provided, but with VLLM it does not work, even with 80 GB of GPU memory.

I try:

python -u -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --model NousResearch/Yarn-Mistral-7b-128k --trust-remote-code

and i get:

  File "/home/azureuser/.local/lib/python3.10/site-packages/vllm/model_executor/layers/attention.py", line 266, in forward
    self.multi_query_kv_attention(
  File "/home/azureuser/.local/lib/python3.10/site-packages/vllm/model_executor/layers/attention.py", line 117, in multi_query_kv_attention
    key = torch.repeat_interleave(key, self.num_queries_per_kv, dim=1)
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

Any idea about how to fix that?

Thanks a lot.

anione

Nov 27, 2023

vLLM v0.2.2 was just released, which includes Yarn support, so maybe it will work for you now!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment