Instructions to use mickume/harry_potter_tiny_mistral_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mickume/harry_potter_tiny_mistral_7b with Transformers:

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

pipe = pipeline("text-generation", model="mickume/harry_potter_tiny_mistral_7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mickume/harry_potter_tiny_mistral_7b")
model = AutoModelForCausalLM.from_pretrained("mickume/harry_potter_tiny_mistral_7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mickume/harry_potter_tiny_mistral_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mickume/harry_potter_tiny_mistral_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mickume/harry_potter_tiny_mistral_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mickume/harry_potter_tiny_mistral_7b

SGLang

How to use mickume/harry_potter_tiny_mistral_7b 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 "mickume/harry_potter_tiny_mistral_7b" \
    --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": "mickume/harry_potter_tiny_mistral_7b",
		"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 "mickume/harry_potter_tiny_mistral_7b" \
        --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": "mickume/harry_potter_tiny_mistral_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mickume/harry_potter_tiny_mistral_7b with Docker Model Runner:
```
docker model run hf.co/mickume/harry_potter_tiny_mistral_7b
```

mickume commited on Oct 25, 2023

Commit

d30b508

1 Parent(s): ba991fc

Upload MistralForCausalLM

Browse files

Files changed (3) hide show

pytorch_model-00001-of-00003.bin +1 -1
pytorch_model-00002-of-00003.bin +1 -1
pytorch_model-00003-of-00003.bin +1 -1

pytorch_model-00001-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7998f26cd51b444effaa6fe8c54199d3d66c7fe35de08366cd6c2c7304e8c57
 size 4943185632

 version https://git-lfs.github.com/spec/v1
+oid sha256:cbb038057a947a563064f4271cf4650764b73b140730695bb0bca072be1020e4
 size 4943185632

pytorch_model-00002-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe7ecc2b3f6c7d50a24fde8841c2fde1abd40d11334a91b1c6d2ef19154bace
 size 4999844744

 version https://git-lfs.github.com/spec/v1
+oid sha256:3bed630c4ad54fae41b2dbfef8e63dfeeb5921d5e13791b4be9b5dc83b202389
 size 4999844744

pytorch_model-00003-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99f39e938809afeb2430f7e89e5d3ddbab4c80e44c2f28923aa618086835199
 size 4540537414

 version https://git-lfs.github.com/spec/v1
+oid sha256:6ee31378ae82b3d8fa18a53961d6d418cede4580510faeb5ea3d12449b2d7e2e
 size 4540537414