Instructions to use Sela223/173 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Sela223/173 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Sela223/173", filename="sela173-Q4_K_M.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 Sela223/173 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Sela223/173:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Sela223/173:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Sela223/173:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Sela223/173: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 Sela223/173:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Sela223/173: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 Sela223/173:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sela223/173:Q4_K_M
Use Docker
docker model run hf.co/Sela223/173:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Sela223/173 with Ollama:
ollama run hf.co/Sela223/173:Q4_K_M
- Unsloth Studio new
How to use Sela223/173 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 Sela223/173 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 Sela223/173 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Sela223/173 to start chatting
- Docker Model Runner
How to use Sela223/173 with Docker Model Runner:
docker model run hf.co/Sela223/173:Q4_K_M
- Lemonade
How to use Sela223/173 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sela223/173:Q4_K_M
Run and chat with the model
lemonade run user.173-Q4_K_M
List all available models
lemonade list
| { | |
| "architectures": [ | |
| "Gemma3nForConditionalGeneration" | |
| ], | |
| "audio_config": { | |
| "conf_attention_chunk_size": 12, | |
| "conf_attention_context_left": 13, | |
| "conf_attention_context_right": 0, | |
| "conf_attention_logit_cap": 50.0, | |
| "conf_conv_kernel_size": 5, | |
| "conf_num_attention_heads": 8, | |
| "conf_num_hidden_layers": 12, | |
| "conf_positional_bias_size": 256, | |
| "conf_reduction_factor": 4, | |
| "conf_residual_weight": 0.5, | |
| "gradient_clipping": 10000000000.0, | |
| "hidden_size": 1536, | |
| "input_feat_size": 128, | |
| "model_type": "gemma3n_audio", | |
| "rms_norm_eps": 1e-06, | |
| "sscp_conv_channel_size": [ | |
| 128, | |
| 32 | |
| ], | |
| "sscp_conv_eps": 0.001, | |
| "sscp_conv_group_norm_eps": 0.001, | |
| "sscp_conv_kernel_size": [ | |
| [ | |
| 3, | |
| 3 | |
| ], | |
| [ | |
| 3, | |
| 3 | |
| ] | |
| ], | |
| "sscp_conv_stride_size": [ | |
| [ | |
| 2, | |
| 2 | |
| ], | |
| [ | |
| 2, | |
| 2 | |
| ] | |
| ], | |
| "torch_dtype": "float32", | |
| "vocab_offset": 262272, | |
| "vocab_size": 128 | |
| }, | |
| "audio_soft_tokens_per_image": 188, | |
| "audio_token_id": 262273, | |
| "boa_token_id": 256000, | |
| "boi_token_id": 255999, | |
| "eoa_token_id": 262272, | |
| "eoi_token_id": 262144, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_id": 262145, | |
| "initializer_range": 0.02, | |
| "model_type": "gemma3n", | |
| "text_config": { | |
| "activation_sparsity_pattern": [ | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.95, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "altup_active_idx": 0, | |
| "altup_coef_clip": 120.0, | |
| "altup_correct_scale": true, | |
| "altup_lr_multiplier": 1.0, | |
| "altup_num_inputs": 4, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "final_logit_softcapping": 30.0, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2048, | |
| "hidden_size_per_layer_input": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": [ | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384, | |
| 16384 | |
| ], | |
| "laurel_rank": 64, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "model_type": "gemma3n_text", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 35, | |
| "num_key_value_heads": 2, | |
| "num_kv_shared_layers": 15, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 512, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 262400, | |
| "vocab_size_per_layer_input": 262144 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.54.0.dev0", | |
| "vision_config": { | |
| "architecture": "mobilenetv5_300m_enc", | |
| "do_pooling": true, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "label_names": [ | |
| "LABEL_0", | |
| "LABEL_1" | |
| ], | |
| "model_args": null, | |
| "model_type": "gemma3n_vision", | |
| "num_classes": 2, | |
| "rms_norm_eps": 1e-06, | |
| "torch_dtype": "float32", | |
| "vocab_offset": 262144, | |
| "vocab_size": 128 | |
| }, | |
| "vision_soft_tokens_per_image": 256 | |
| } | |