Instructions to use pphan720/qwen3_4b_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use pphan720/qwen3_4b_base with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf pphan720/qwen3_4b_base:Q4_K_M # Run inference directly in the terminal: llama cli -hf pphan720/qwen3_4b_base:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf pphan720/qwen3_4b_base:Q4_K_M # Run inference directly in the terminal: llama cli -hf pphan720/qwen3_4b_base:Q4_K_M
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 pphan720/qwen3_4b_base:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf pphan720/qwen3_4b_base:Q4_K_M
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 pphan720/qwen3_4b_base:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf pphan720/qwen3_4b_base:Q4_K_M
Use Docker
docker model run hf.co/pphan720/qwen3_4b_base:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use pphan720/qwen3_4b_base with Ollama:
ollama run hf.co/pphan720/qwen3_4b_base:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use pphan720/qwen3_4b_base with Docker Model Runner:
docker model run hf.co/pphan720/qwen3_4b_base:Q4_K_M
- Lemonade
How to use pphan720/qwen3_4b_base with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull pphan720/qwen3_4b_base:Q4_K_M
Run and chat with the model
lemonade run user.qwen3_4b_base-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Trained with Unsloth - config
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"num_attention_heads": 32,
|
| 56 |
"num_hidden_layers": 36,
|
| 57 |
"num_key_value_heads": 8,
|
| 58 |
-
"pad_token_id":
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
| 61 |
"rope_theta": 1000000,
|
|
|
|
| 55 |
"num_attention_heads": 32,
|
| 56 |
"num_hidden_layers": 36,
|
| 57 |
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151669,
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
| 61 |
"rope_theta": 1000000,
|