Sentence Similarity
MLX
Safetensors
lfm2
lfm2.5
embeddings
feature-extraction
retrieval
8-bit precision
quantized
custom_code
Instructions to use mlx-community/LFM2.5-Embedding-350M-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/LFM2.5-Embedding-350M-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LFM2.5-Embedding-350M-8bit mlx-community/LFM2.5-Embedding-350M-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "architectures": [ | |
| "Lfm2BidirectionalModel" | |
| ], | |
| "block_auto_adjust_ff_dim": true, | |
| "block_dim": 1024, | |
| "block_ff_dim": 6656, | |
| "block_ffn_dim_multiplier": 1.0, | |
| "block_mlp_init_scale": 1.0, | |
| "block_multiple_of": 256, | |
| "block_norm_eps": 1e-05, | |
| "block_out_init_scale": 1.0, | |
| "block_use_swiglu": true, | |
| "block_use_xavier_init": true, | |
| "bos_token_id": 1, | |
| "conv_L_cache": 3, | |
| "conv_bias": false, | |
| "conv_dim": 1024, | |
| "conv_use_xavier_init": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 7, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6656, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "model_type": "lfm2", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 16, | |
| "num_heads": 16, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "tie_embedding": true, | |
| "transformers_version": "4.56.2", | |
| "use_cache": true, | |
| "use_pos_enc": true, | |
| "vocab_size": 65536, | |
| "auto_map": { | |
| "AutoModel": "modeling_lfm2_bidirectional.Lfm2BidirectionalModel" | |
| }, | |
| "mlx": { | |
| "head": "embedding", | |
| "pooling": "cls", | |
| "prompts": { | |
| "query": "query: ", | |
| "document": "document: " | |
| } | |
| }, | |
| "quantization": { | |
| "mode": "affine", | |
| "bits": 8, | |
| "group_size": 64 | |
| } | |
| } |