d1-3B on Core AI: the Mac fp16 and iPhone int8mlp decoders (64 tokens a call, hidden output, option-token readout on the host) and the fp16w32 vision tower, debug locations stripped; card, LICENSE (LFM Open License v1.0), config.json, SHA256SUMS
3cf8b7c verified Download config.json from mlboydaisuke/d1-3B-CoreAI: direct link, hf CLI and curl.
- Browser
- Download file 2.77 kB
-
https://huggingface.co/mlboydaisuke/d1-3B-CoreAI/resolve/main/config.json
- Command line
-
hf download hf://mlboydaisuke/d1-3B-CoreAI/config.json
-
curl -L -o config.json https://huggingface.co/mlboydaisuke/d1-3B-CoreAI/resolve/main/config.json
2.77 kB
| { | |
| "architectures": [ | |
| "Lfm2VlForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoModel": "modeling_d1.D1Model" | |
| }, | |
| "bos_token_id": 124894, | |
| "do_image_splitting": true, | |
| "do_resize": true, | |
| "downsample_factor": 2, | |
| "dtype": "bfloat16", | |
| "encoder_patch_size": 16, | |
| "eos_token_id": 124900, | |
| "image_token_id": 124907, | |
| "max_image_tokens": 256, | |
| "max_num_patches": 1024, | |
| "max_pixels_tolerance": 2.0, | |
| "max_tiles": 10, | |
| "min_image_tokens": 64, | |
| "min_tiles": 2, | |
| "model_type": "lfm2_vl", | |
| "pad_token_id": 124893, | |
| "projector_bias": true, | |
| "projector_hidden_act": "gelu", | |
| "projector_hidden_size": 2048, | |
| "projector_use_layernorm": false, | |
| "text_config": { | |
| "architectures": [ | |
| "Lfm2ForCausalLM" | |
| ], | |
| "block__name_mlp": "parallel_mlp_merged", | |
| "block_auto_adjust_ff_dim": false, | |
| "block_dim": 2048, | |
| "block_ffn_dim_multiplier": 1.0, | |
| "block_multiple_of": 256, | |
| "block_norm_eps": 1e-05, | |
| "block_use_swiglu": true, | |
| "bos_token_id": 124894, | |
| "conv_L_cache": 3, | |
| "conv_bias": false, | |
| "conv_dim": 2048, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 124900, | |
| "full_attn_idxs": null, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10752, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "model_type": "lfm2", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_heads": 32, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 8, | |
| "output_softcap": 0.0, | |
| "pad_token_id": 124893, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "use_pos_enc": true, | |
| "vocab_size": 128000 | |
| }, | |
| "tie_word_embeddings": true, | |
| "tile_size": 512, | |
| "transformers_version": "5.14.1", | |
| "use_image_special_tokens": true, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip2_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_patches": 256, | |
| "patch_size": 16, | |
| "vision_use_head": false | |
| } | |
| } | |