Instructions to use jartine/phi-2-llamafile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jartine/phi-2-llamafile with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jartine/phi-2-llamafile")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jartine/phi-2-llamafile", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jartine/phi-2-llamafile with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jartine/phi-2-llamafile" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jartine/phi-2-llamafile", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jartine/phi-2-llamafile
- SGLang
How to use jartine/phi-2-llamafile 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 "jartine/phi-2-llamafile" \ --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": "jartine/phi-2-llamafile", "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 "jartine/phi-2-llamafile" \ --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": "jartine/phi-2-llamafile", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jartine/phi-2-llamafile with Docker Model Runner:
docker model run hf.co/jartine/phi-2-llamafile
Quantize phi-2 with llamafile-0.7.3 Q4_1
Browse files- .gitattributes +1 -0
- phi-2.Q4_1.llamafile +3 -0
.gitattributes
CHANGED
|
@@ -59,3 +59,4 @@ phi-2.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
|
|
| 59 |
phi-2.Q8_0.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 60 |
phi-2.F16.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 61 |
phi-2.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 59 |
phi-2.Q8_0.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 60 |
phi-2.F16.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 61 |
phi-2.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
phi-2.Q4_1.llamafile filter=lfs diff=lfs merge=lfs -text
|
phi-2.Q4_1.llamafile
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:909b3de714190b3a2434a754eaeed371f6bbe1ca49b715e4030509626c14dbb2
|
| 3 |
+
size 1792283076
|