CoolFace
Modelpublic

InsightKeeper/FastVLM-1.5B-MLX-4bit

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes23downloads
config.json49 linesDownload Raw Back to root
1{2    "architectures": [3        "LlavaQwen2ForCausalLM"4    ],5    "attention_dropout": 0.0,6    "bos_token_id": 151643,7    "eos_token_id": 151645,8    "freeze_mm_mlp_adapter": false,9    "hidden_act": "silu",10    "hidden_size": 1536,11    "image_aspect_ratio": "pad",12    "image_grid_pinpoints": null,13    "image_token_index": 151646,14    "initializer_range": 0.02,15    "intermediate_size": 8960,16    "max_position_embeddings": 32768,17    "max_window_layers": 28,18    "mm_hidden_size": 3072,19    "mm_patch_merge_type": "flat",20    "mm_projector_lr": null,21    "mm_projector_type": "mlp2x_gelu",22    "mm_use_im_patch_token": false,23    "mm_use_im_start_end": false,24    "mm_vision_select_feature": "patch",25    "mm_vision_select_layer": -2,26    "mm_vision_tower": "mobileclip_l_1024",27    "model_type": "llava_qwen2",28    "num_attention_heads": 12,29    "num_hidden_layers": 28,30    "num_key_value_heads": 2,31    "quantization": {32        "group_size": 64,33        "bits": 434    },35    "rms_norm_eps": 1e-06,36    "rope_theta": 1000000.0,37    "sliding_window": 32768,38    "tie_word_embeddings": false,39    "tokenizer_model_max_length": 8192,40    "tokenizer_padding_side": "right",41    "transformers_version": "4.39.3",42    "tune_mm_mlp_adapter": false,43    "unfreeze_mm_vision_tower": true,44    "use_cache": true,45    "use_mm_proj": true,46    "use_sliding_window": false,47    "vision_config": {},48    "vocab_size": 15193649}