Instructions to use leafspark/Mistral-Large-218B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leafspark/Mistral-Large-218B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="leafspark/Mistral-Large-218B-Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("leafspark/Mistral-Large-218B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("leafspark/Mistral-Large-218B-Instruct")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use leafspark/Mistral-Large-218B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leafspark/Mistral-Large-218B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/Mistral-Large-218B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/leafspark/Mistral-Large-218B-Instruct

SGLang

How to use leafspark/Mistral-Large-218B-Instruct 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 "leafspark/Mistral-Large-218B-Instruct" \
    --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": "leafspark/Mistral-Large-218B-Instruct",
		"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 "leafspark/Mistral-Large-218B-Instruct" \
        --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": "leafspark/Mistral-Large-218B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use leafspark/Mistral-Large-218B-Instruct with Docker Model Runner:
```
docker model run hf.co/leafspark/Mistral-Large-218B-Instruct
```

leafspark commited on Jul 29, 2024

Commit

b8da283

verified ·

1 Parent(s): c2e478c

model: add 5 chunks (47-51)

Browse files

Files changed (5) hide show

model-00047-of-00158.safetensors +3 -0
model-00048-of-00158.safetensors +3 -0
model-00049-of-00158.safetensors +3 -0
model-00050-of-00158.safetensors +3 -0
model-00051-of-00158.safetensors +3 -0

model-00047-of-00158.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b56da21652c71de8ff1675a4caec6315c74bfa371577ebd873ec1cf81d321c2
+size 2768290848

model-00048-of-00158.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4768a14fab07b78484d104b6b67bf6c73a6b89efabe625991dc468f23e4c0d1
+size 2768290848

model-00049-of-00158.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c8270586000640385778b83f7b8aa6b37fa0549cf0fe9b5e0756beb1525165fc
+size 2768290848

model-00050-of-00158.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c6cfab1ca92d423f8d354995e5291340f2ec4a597b28f4f3fbb0f3d00ac85e75
+size 2768290848

model-00051-of-00158.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3f97b40d0a0bbd8f5428048e1d43c1724c5d9cd782ea585c2df6c8468748fd
+size 2768290848