| { |
| "_mlp_class": "LLaMAMLP", |
| "_name_or_path": "./checkpoints/mobilellama-2.7b-chat", |
| "_norm_class": "RMSNorm", |
| "architectures": [ |
| "LlavaLlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bias": false, |
| "block_size": 2048, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "freeze_mm_mlp_adapter": false, |
| "gelu_approximate": "none", |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "image_aspect_ratio": "pad", |
| "initializer_range": 0.02, |
| "intermediate_size": 6912, |
| "lm_head_bias": false, |
| "max_position_embeddings": 2048, |
| "mm_hidden_size": 1024, |
| "mm_patch_merge_type": "flat", |
| "mm_projector_lr": null, |
| "mm_projector_type": "mlp2x_gelu", |
| "mm_use_im_patch_token": false, |
| "mm_use_im_start_end": false, |
| "mm_vision_select_feature": "patch", |
| "mm_vision_select_layer": -2, |
| "mm_vision_tower": "./checkpoints/clip-vit-large-patch14-336", |
| "model_type": "llava_llama", |
| "n_embd": 2560, |
| "n_head": 16, |
| "n_layer": 32, |
| "n_query_groups": 16, |
| "name": "huggy_llama_3b", |
| "norm_eps": 1e-06, |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "org": "meta", |
| "pad_token_id": 0, |
| "padded_vocab_size": 32000, |
| "padding_multiple": 64, |
| "parallel_residual": false, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_base": 10000, |
| "rope_condense_ratio": 1, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "rotary_percentage": 1.0, |
| "shared_attention_norm": false, |
| "tie_word_embeddings": false, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.37.2", |
| "tune_mm_mlp_adapter": false, |
| "use_cache": true, |
| "use_mm_proj": true, |
| "vocab_size": 32000 |
| } |
|
|