| { |
| "activation_type": "swiglu", |
| "alibi": false, |
| "alibi_bias_max": 8.0, |
| "architectures": [ |
| "LlavaOLMoBitnet1BForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "attention_layer_norm": false, |
| "attention_layer_norm_with_affine": false, |
| "auto_map": { |
| "AutoConfig": "configuration_olmo.OLMoConfig", |
| "AutoModelForCausalLM": "modeling_olmo.OLMoForCausalLM" |
| }, |
| "bias_for_layer_norm": false, |
| "block_group_size": 1, |
| "block_type": "sequential", |
| "bos_token_id": 50279, |
| "clip_qkv": null, |
| "d_model": 2048, |
| "embedding_dropout": 0.0, |
| "embedding_size": 50304, |
| "eos_token_id": 50279, |
| "flash_attention": true, |
| "freeze_mm_mlp_adapter": false, |
| "freeze_mm_vision_resampler": false, |
| "image_aspect_ratio": "pad", |
| "include_bias": false, |
| "inference_mode": false, |
| "init_cutoff_factor": null, |
| "init_device": "cpu", |
| "init_fn": "mitchell", |
| "init_std": 0.02, |
| "layer_norm_type": "rms", |
| "layer_norm_with_affine": true, |
| "max_sequence_length": 2048, |
| "mlp_hidden_size": null, |
| "mlp_ratio": 8, |
| "mm_hidden_size": 1024, |
| "mm_patch_merge_type": "flat", |
| "mm_projector_lr": null, |
| "mm_projector_type": "mlp2x_gelu", |
| "mm_resampler_type": null, |
| "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": "openai/clip-vit-large-patch14-336", |
| "model_type": "IntelLabs/LlavaOLMoBitnet1B", |
| "multi_query_attention": false, |
| "n_heads": 16, |
| "n_kv_heads": null, |
| "n_layers": 16, |
| "pad_token_id": 1, |
| "precision": "amp_bf16", |
| "residual_dropout": 0.0, |
| "rope": true, |
| "rope_full_precision": true, |
| "scale_logits": false, |
| "ternary": true, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "float32", |
| "transformers_version": "4.37.2", |
| "tune_mm_mlp_adapter": false, |
| "tune_mm_vision_resampler": false, |
| "unfreeze_mm_vision_tower": false, |
| "use_cache": true, |
| "use_mm_proj": true, |
| "vocab_size": 50280, |
| "weight_tying": true |
| } |
|
|
