Instructions to use hongyongjiang/python-reference-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hongyongjiang/python-reference-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hongyongjiang/python-reference-models",
	filename="gemma-3-4b-it_bin/gemma-3-4b-it-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use hongyongjiang/python-reference-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hongyongjiang/python-reference-models:F16
# Run inference directly in the terminal:
llama-cli -hf hongyongjiang/python-reference-models:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hongyongjiang/python-reference-models:F16
# Run inference directly in the terminal:
llama-cli -hf hongyongjiang/python-reference-models:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf hongyongjiang/python-reference-models:F16
# Run inference directly in the terminal:
./llama-cli -hf hongyongjiang/python-reference-models:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf hongyongjiang/python-reference-models:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hongyongjiang/python-reference-models:F16

Use Docker

docker model run hf.co/hongyongjiang/python-reference-models:F16

LM Studio
Jan
Ollama
How to use hongyongjiang/python-reference-models with Ollama:
```
ollama run hf.co/hongyongjiang/python-reference-models:F16
```

Unsloth Studio new

How to use hongyongjiang/python-reference-models with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hongyongjiang/python-reference-models to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hongyongjiang/python-reference-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hongyongjiang/python-reference-models to start chatting

Docker Model Runner
How to use hongyongjiang/python-reference-models with Docker Model Runner:
```
docker model run hf.co/hongyongjiang/python-reference-models:F16
```

Lemonade

How to use hongyongjiang/python-reference-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hongyongjiang/python-reference-models:F16

Run and chat with the model

lemonade run user.python-reference-models-F16

List all available models

lemonade list

hongyongjiang commited on Mar 27

Commit

51ca989

verified ·

1 Parent(s): 2799d27

Delete files qwen3-vl-4b-dp/ with huggingface_hub

Browse files

Files changed (5) hide show

qwen3-vl-4b-dp/acts.pt +0 -3
qwen3-vl-4b-dp/model.pt +0 -3
qwen3-vl-4b-dp/scale.pt +0 -3
qwen3-vl-4b-dp/smooth.pt +0 -3
qwen3-vl-4b-dp/wgts.pt +0 -3

qwen3-vl-4b-dp/acts.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a931f2b9373fc5d63f2d8386a808f56245ddd5e772428177a6c6a16fcdc2523
-size 55975

qwen3-vl-4b-dp/model.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3109e254938ff3d66477b10880bda5bf744bfc9be66c08755765fa5d67fad30c
-size 8045090783

qwen3-vl-4b-dp/scale.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dcaf2e8164bc08707382108563f164c79a67aa315a10918eec8de7b4189e2f96
-size 4566483

qwen3-vl-4b-dp/smooth.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5a4772a5bc2c0594bade56d31693cee385c522bc1773278ca9c18dbec22f14f6
-size 2773543

qwen3-vl-4b-dp/wgts.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cdde16b81c020527f418e855715261a92f4aca0a994c54cbdb9dcb14f1bcbf3c
-size 4519327