Team Ai
Modelpublic

trl-internal-testing/tiny-Qwen3_5ForConditionalGeneration-NoThink

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes99kdownloads
config.json79 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3_5ForConditionalGeneration"4  ],5  "dtype": "bfloat16",6  "image_token_id": 248056,7  "model_type": "qwen3_5",8  "text_config": {9    "attention_bias": false,10    "attention_dropout": 0.0,11    "attn_output_gate": true,12    "bos_token_id": null,13    "dtype": "bfloat16",14    "eos_token_id": 248044,15    "full_attention_interval": 2,16    "head_dim": 256,17    "hidden_act": "silu",18    "hidden_size": 16,19    "initializer_range": 0.02,20    "intermediate_size": 3584,21    "layer_types": [22      "linear_attention",23      "full_attention"24    ],25    "linear_conv_kernel_dim": 4,26    "linear_key_head_dim": 128,27    "linear_num_key_heads": 16,28    "linear_num_value_heads": 16,29    "linear_value_head_dim": 128,30    "mamba_ssm_dtype": "float32",31    "max_position_embeddings": 262144,32    "mlp_only_layers": [],33    "model_type": "qwen3_5_text",34    "mtp_num_hidden_layers": 1,35    "mtp_use_dedicated_embeddings": false,36    "num_attention_heads": 4,37    "num_hidden_layers": 2,38    "num_key_value_heads": 2,39    "pad_token_id": null,40    "partial_rotary_factor": 0.25,41    "rms_norm_eps": 1e-06,42    "rope_parameters": {43      "mrope_interleaved": true,44      "mrope_section": [45        11,46        11,47        1048      ],49      "partial_rotary_factor": 0.25,50      "rope_theta": 10000000,51      "rope_type": "default"52    },53    "tie_word_embeddings": true,54    "use_cache": true,55    "vocab_size": 24832056  },57  "tie_word_embeddings": true,58  "transformers_version": "5.2.0",59  "video_token_id": 248057,60  "vision_config": {61    "deepstack_visual_indexes": [],62    "depth": 2,63    "hidden_act": "gelu_pytorch_tanh",64    "hidden_size": 16,65    "in_channels": 3,66    "initializer_range": 0.02,67    "intermediate_size": 32,68    "model_type": "qwen3_5",69    "num_heads": 4,70    "num_position_embeddings": 2304,71    "out_hidden_size": 16,72    "patch_size": 16,73    "spatial_merge_size": 2,74    "temporal_patch_size": 275  },76  "vision_end_token_id": 248054,77  "vision_start_token_id": 24805378}79