| { |
| "_name_or_path": "TranscoreM", |
| "architectures": [ |
| "TransCoreMQWenForCausalLM" |
| ], |
| "attn_dropout_prob": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_qwen.QWenConfig", |
| "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel" |
| }, |
| "bf16": false, |
| "emb_dropout_prob": 0.0, |
| "fp16": false, |
| "fp32": false, |
| "freeze_mm_mlp_adapter": false, |
| "hidden_size": 5120, |
| "image_aspect_ratio": "pad", |
| "image_grid_pinpoints": null, |
| "initializer_range": 0.02, |
| "intermediate_size": 27392, |
| "kv_channels": 128, |
| "layer_norm_epsilon": 1e-06, |
| "max_position_embeddings": 8192, |
| "mm_hidden_size": 1024, |
| "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": "PCIResearch/clip-vit-large-patch14-336", |
| "model_type": "transcorem", |
| "no_bias": true, |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "onnx_safe": null, |
| "rotary_emb_base": 10000, |
| "rotary_pct": 1.0, |
| "scale_attn_weights": true, |
| "seq_length": 2048, |
| "softmax_in_fp32": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": "QWenTokenizer", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.31.0", |
| "tune_entire_model": false, |
| "tune_mm_mlp_adapter": false, |
| "tune_vision_tower": false, |
| "use_cache": true, |
| "use_cache_kernel": false, |
| "use_cache_quantization": false, |
| "use_dynamic_ntk": true, |
| "use_flash_attn": "auto", |
| "use_logn_attn": true, |
| "use_mm_proj": true, |
| "vision_tower_lr": null, |
| "vocab_size": 152064 |
| } |
|
|