Instructions to use whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16 --local-dir LycheeAI-coder-2b-II-pro-MLX-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16: direct link, hf CLI and curl.
- Browser
- Download file 681 Bytes
-
https://huggingface.co/whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16/resolve/main/config.json
- Command line
-
hf download hf://whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16/config.json
-
curl -L -o config.json https://huggingface.co/whcl412/LycheeAI-coder-2b-II-pro-MLX-bf16/resolve/main/config.json
681 Bytes
| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 0, | |
| "eos_token_id": [ | |
| 1, | |
| 130073 | |
| ], | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 131072, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 42, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "5.6.2", | |
| "use_cache": true, | |
| "vocab_size": 130560 | |
| } |