CoolFace
Modelpublic

onnx-internal-testing/tiny-random-Qwen3_5ForConditionalGeneration

sourceHugging Faceupdated 7mo agoView on Hugging Face
0likes3.5kdownloads
config.json95 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": 4,16    "head_dim": 32,17    "hidden_act": "silu",18    "hidden_size": 8,19    "initializer_range": 0.02,20    "intermediate_size": 32,21    "layer_types": [22      "linear_attention",23      "linear_attention",24      "linear_attention",25      "full_attention"26    ],27    "linear_conv_kernel_dim": 4,28    "linear_key_head_dim": 32,29    "linear_num_key_heads": 4,30    "linear_num_value_heads": 8,31    "linear_value_head_dim": 32,32    "mamba_ssm_dtype": "float32",33    "max_position_embeddings": 262144,34    "mlp_only_layers": [],35    "model_type": "qwen3_5_text",36    "mtp_num_hidden_layers": 1,37    "mtp_use_dedicated_embeddings": false,38    "num_attention_heads": 8,39    "num_hidden_layers": 4,40    "num_key_value_heads": 4,41    "pad_token_id": null,42    "partial_rotary_factor": 0.25,43    "rms_norm_eps": 1e-06,44    "rope_parameters": {45      "mrope_interleaved": true,46      "mrope_section": [47        1,48        1,49        250      ],51      "partial_rotary_factor": 0.25,52      "rope_theta": 10000000,53      "rope_type": "default"54    },55    "tie_word_embeddings": false,56    "use_cache": true,57    "vocab_size": 24832058  },59  "tie_word_embeddings": false,60  "transformers_version": "5.3.0.dev0",61  "video_token_id": 248057,62  "vision_config": {63    "deepstack_visual_indexes": [],64    "depth": 2,65    "dtype": "bfloat16",66    "hidden_act": "gelu_pytorch_tanh",67    "hidden_size": 64,68    "in_channels": 3,69    "initializer_range": 0.02,70    "intermediate_size": 128,71    "model_type": "qwen3_5",72    "num_heads": 2,73    "num_position_embeddings": 2304,74    "out_hidden_size": 8,75    "patch_size": 16,76    "spatial_merge_size": 2,77    "temporal_patch_size": 278  },79  "vision_end_token_id": 248054,80  "vision_start_token_id": 248053,81  "transformers.js_config": {82    "use_external_data_format": {83      "vision_encoder.onnx": 1,84      "decoder_model_merged.onnx": 1,85      "embed_tokens.onnx": 1,86      "vision_encoder_fp16.onnx": 1,87      "decoder_model_merged_fp16.onnx": 1,88      "embed_tokens_fp16.onnx": 189    },90    "kv_cache_dtype": {91      "q4f16": "float16",92      "fp16": "float16"93    }94  }95}