| { |
| "architectures": [ |
| "QTSplusInternLM2_ForCausalLM" |
| ], |
| "attn_implementation": "flash_attention_2", |
| "auto_map": { |
| "AutoConfig": "qts_plus_internlm2_lm.QTSplusInternLM2_CausalLM_Config", |
| "AutoModelForCausalLM": "qts_plus_internlm2_lm.QTSplusInternLM2_ForCausalLM", |
| "AutoProcessor": "processing_qts_plus_internvl2_5.QTSplusInternVL2_5_Processor" |
| }, |
| "bias": false, |
| "bos_token_id": 1, |
| "downsample_ratio": 0.5, |
| "dtype": "bfloat16", |
| "enable_qts_plus": true, |
| "eos_token_id": 2, |
| "force_image_size": 448, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "image_token_id": 92546, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "lambda_m": 0, |
| "lambda_s": 0, |
| "lambda_t": 0, |
| "llm_hidden_size": 4096, |
| "max_position_embeddings": 32768, |
| "model_type": "qts_plus_internlm2_causal_lm", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "out_hidden_size": 4096, |
| "pad_token_id": 2, |
| "pretraining_tp": 1, |
| "project_text_if_needed": false, |
| "ps_version": "v2", |
| "qts_plus_block_dropout": 0.0, |
| "qts_plus_nmax": 25600, |
| "qts_plus_reencode": false, |
| "qts_plus_reencode_layers": 0, |
| "qts_plus_rho_max": 0.5, |
| "qts_plus_rho_min": 0.05, |
| "qts_plus_scoring_layers": 4, |
| "qts_plus_tau_s": 0.1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 2.0, |
| "type": "dynamic" |
| }, |
| "rope_theta": 1000000, |
| "select_layer": -1, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.57.6", |
| "use_bfloat16": true, |
| "use_cache": true, |
| "vision_config": { |
| "architectures": [ |
| "InternVisionModel" |
| ], |
| "attention_dropout": 0.0, |
| "drop_path_rate": 0.0, |
| "dropout": 0.0, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu", |
| "hidden_size": 1024, |
| "image_size": 448, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-06, |
| "model_type": "intern_vit_6b", |
| "norm_type": "layer_norm", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "patch_size": 14, |
| "qk_normalization": false, |
| "qkv_bias": true, |
| "use_bfloat16": true, |
| "use_flash_attn": true |
| }, |
| "vision_embed_size": 4096, |
| "vision_tower": "internvl2_5_vision", |
| "vocab_size": 92553 |
| } |
|
|
