初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/Qwen2.5-VL-3B-Instruct-quantized.w8a8 Source: Original Platform
This commit is contained in:
265
config.json
Normal file
265
config.json
Normal file
@@ -0,0 +1,265 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_token_id": 151654,
|
||||
"image_token_id": 151655,
|
||||
"video_token_id": 151656,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.41.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"quantization_config": {
|
||||
"config_groups": {
|
||||
"group_0": {
|
||||
"input_activations": {
|
||||
"actorder": null,
|
||||
"block_structure": null,
|
||||
"dynamic": true,
|
||||
"group_size": null,
|
||||
"num_bits": 8,
|
||||
"observer": null,
|
||||
"observer_kwargs": {},
|
||||
"strategy": "token",
|
||||
"symmetric": true,
|
||||
"type": "int"
|
||||
},
|
||||
"output_activations": null,
|
||||
"targets": [
|
||||
"Linear"
|
||||
],
|
||||
"weights": {
|
||||
"actorder": null,
|
||||
"block_structure": null,
|
||||
"dynamic": false,
|
||||
"group_size": null,
|
||||
"num_bits": 8,
|
||||
"observer": "minmax",
|
||||
"observer_kwargs": {},
|
||||
"strategy": "channel",
|
||||
"symmetric": true,
|
||||
"type": "int"
|
||||
}
|
||||
}
|
||||
},
|
||||
"format": "int-quantized",
|
||||
"global_compression_ratio": 1.2350377879852423,
|
||||
"ignore": [
|
||||
"visual.blocks.0.attn.qkv",
|
||||
"visual.blocks.0.attn.proj",
|
||||
"visual.blocks.0.mlp.gate_proj",
|
||||
"visual.blocks.0.mlp.up_proj",
|
||||
"visual.blocks.0.mlp.down_proj",
|
||||
"visual.blocks.1.attn.qkv",
|
||||
"visual.blocks.1.attn.proj",
|
||||
"visual.blocks.1.mlp.gate_proj",
|
||||
"visual.blocks.1.mlp.up_proj",
|
||||
"visual.blocks.1.mlp.down_proj",
|
||||
"visual.blocks.2.attn.qkv",
|
||||
"visual.blocks.2.attn.proj",
|
||||
"visual.blocks.2.mlp.gate_proj",
|
||||
"visual.blocks.2.mlp.up_proj",
|
||||
"visual.blocks.2.mlp.down_proj",
|
||||
"visual.blocks.3.attn.qkv",
|
||||
"visual.blocks.3.attn.proj",
|
||||
"visual.blocks.3.mlp.gate_proj",
|
||||
"visual.blocks.3.mlp.up_proj",
|
||||
"visual.blocks.3.mlp.down_proj",
|
||||
"visual.blocks.4.attn.qkv",
|
||||
"visual.blocks.4.attn.proj",
|
||||
"visual.blocks.4.mlp.gate_proj",
|
||||
"visual.blocks.4.mlp.up_proj",
|
||||
"visual.blocks.4.mlp.down_proj",
|
||||
"visual.blocks.5.attn.qkv",
|
||||
"visual.blocks.5.attn.proj",
|
||||
"visual.blocks.5.mlp.gate_proj",
|
||||
"visual.blocks.5.mlp.up_proj",
|
||||
"visual.blocks.5.mlp.down_proj",
|
||||
"visual.blocks.6.attn.qkv",
|
||||
"visual.blocks.6.attn.proj",
|
||||
"visual.blocks.6.mlp.gate_proj",
|
||||
"visual.blocks.6.mlp.up_proj",
|
||||
"visual.blocks.6.mlp.down_proj",
|
||||
"visual.blocks.7.attn.qkv",
|
||||
"visual.blocks.7.attn.proj",
|
||||
"visual.blocks.7.mlp.gate_proj",
|
||||
"visual.blocks.7.mlp.up_proj",
|
||||
"visual.blocks.7.mlp.down_proj",
|
||||
"visual.blocks.8.attn.qkv",
|
||||
"visual.blocks.8.attn.proj",
|
||||
"visual.blocks.8.mlp.gate_proj",
|
||||
"visual.blocks.8.mlp.up_proj",
|
||||
"visual.blocks.8.mlp.down_proj",
|
||||
"visual.blocks.9.attn.qkv",
|
||||
"visual.blocks.9.attn.proj",
|
||||
"visual.blocks.9.mlp.gate_proj",
|
||||
"visual.blocks.9.mlp.up_proj",
|
||||
"visual.blocks.9.mlp.down_proj",
|
||||
"visual.blocks.10.attn.qkv",
|
||||
"visual.blocks.10.attn.proj",
|
||||
"visual.blocks.10.mlp.gate_proj",
|
||||
"visual.blocks.10.mlp.up_proj",
|
||||
"visual.blocks.10.mlp.down_proj",
|
||||
"visual.blocks.11.attn.qkv",
|
||||
"visual.blocks.11.attn.proj",
|
||||
"visual.blocks.11.mlp.gate_proj",
|
||||
"visual.blocks.11.mlp.up_proj",
|
||||
"visual.blocks.11.mlp.down_proj",
|
||||
"visual.blocks.12.attn.qkv",
|
||||
"visual.blocks.12.attn.proj",
|
||||
"visual.blocks.12.mlp.gate_proj",
|
||||
"visual.blocks.12.mlp.up_proj",
|
||||
"visual.blocks.12.mlp.down_proj",
|
||||
"visual.blocks.13.attn.qkv",
|
||||
"visual.blocks.13.attn.proj",
|
||||
"visual.blocks.13.mlp.gate_proj",
|
||||
"visual.blocks.13.mlp.up_proj",
|
||||
"visual.blocks.13.mlp.down_proj",
|
||||
"visual.blocks.14.attn.qkv",
|
||||
"visual.blocks.14.attn.proj",
|
||||
"visual.blocks.14.mlp.gate_proj",
|
||||
"visual.blocks.14.mlp.up_proj",
|
||||
"visual.blocks.14.mlp.down_proj",
|
||||
"visual.blocks.15.attn.qkv",
|
||||
"visual.blocks.15.attn.proj",
|
||||
"visual.blocks.15.mlp.gate_proj",
|
||||
"visual.blocks.15.mlp.up_proj",
|
||||
"visual.blocks.15.mlp.down_proj",
|
||||
"visual.blocks.16.attn.qkv",
|
||||
"visual.blocks.16.attn.proj",
|
||||
"visual.blocks.16.mlp.gate_proj",
|
||||
"visual.blocks.16.mlp.up_proj",
|
||||
"visual.blocks.16.mlp.down_proj",
|
||||
"visual.blocks.17.attn.qkv",
|
||||
"visual.blocks.17.attn.proj",
|
||||
"visual.blocks.17.mlp.gate_proj",
|
||||
"visual.blocks.17.mlp.up_proj",
|
||||
"visual.blocks.17.mlp.down_proj",
|
||||
"visual.blocks.18.attn.qkv",
|
||||
"visual.blocks.18.attn.proj",
|
||||
"visual.blocks.18.mlp.gate_proj",
|
||||
"visual.blocks.18.mlp.up_proj",
|
||||
"visual.blocks.18.mlp.down_proj",
|
||||
"visual.blocks.19.attn.qkv",
|
||||
"visual.blocks.19.attn.proj",
|
||||
"visual.blocks.19.mlp.gate_proj",
|
||||
"visual.blocks.19.mlp.up_proj",
|
||||
"visual.blocks.19.mlp.down_proj",
|
||||
"visual.blocks.20.attn.qkv",
|
||||
"visual.blocks.20.attn.proj",
|
||||
"visual.blocks.20.mlp.gate_proj",
|
||||
"visual.blocks.20.mlp.up_proj",
|
||||
"visual.blocks.20.mlp.down_proj",
|
||||
"visual.blocks.21.attn.qkv",
|
||||
"visual.blocks.21.attn.proj",
|
||||
"visual.blocks.21.mlp.gate_proj",
|
||||
"visual.blocks.21.mlp.up_proj",
|
||||
"visual.blocks.21.mlp.down_proj",
|
||||
"visual.blocks.22.attn.qkv",
|
||||
"visual.blocks.22.attn.proj",
|
||||
"visual.blocks.22.mlp.gate_proj",
|
||||
"visual.blocks.22.mlp.up_proj",
|
||||
"visual.blocks.22.mlp.down_proj",
|
||||
"visual.blocks.23.attn.qkv",
|
||||
"visual.blocks.23.attn.proj",
|
||||
"visual.blocks.23.mlp.gate_proj",
|
||||
"visual.blocks.23.mlp.up_proj",
|
||||
"visual.blocks.23.mlp.down_proj",
|
||||
"visual.blocks.24.attn.qkv",
|
||||
"visual.blocks.24.attn.proj",
|
||||
"visual.blocks.24.mlp.gate_proj",
|
||||
"visual.blocks.24.mlp.up_proj",
|
||||
"visual.blocks.24.mlp.down_proj",
|
||||
"visual.blocks.25.attn.qkv",
|
||||
"visual.blocks.25.attn.proj",
|
||||
"visual.blocks.25.mlp.gate_proj",
|
||||
"visual.blocks.25.mlp.up_proj",
|
||||
"visual.blocks.25.mlp.down_proj",
|
||||
"visual.blocks.26.attn.qkv",
|
||||
"visual.blocks.26.attn.proj",
|
||||
"visual.blocks.26.mlp.gate_proj",
|
||||
"visual.blocks.26.mlp.up_proj",
|
||||
"visual.blocks.26.mlp.down_proj",
|
||||
"visual.blocks.27.attn.qkv",
|
||||
"visual.blocks.27.attn.proj",
|
||||
"visual.blocks.27.mlp.gate_proj",
|
||||
"visual.blocks.27.mlp.up_proj",
|
||||
"visual.blocks.27.mlp.down_proj",
|
||||
"visual.blocks.28.attn.qkv",
|
||||
"visual.blocks.28.attn.proj",
|
||||
"visual.blocks.28.mlp.gate_proj",
|
||||
"visual.blocks.28.mlp.up_proj",
|
||||
"visual.blocks.28.mlp.down_proj",
|
||||
"visual.blocks.29.attn.qkv",
|
||||
"visual.blocks.29.attn.proj",
|
||||
"visual.blocks.29.mlp.gate_proj",
|
||||
"visual.blocks.29.mlp.up_proj",
|
||||
"visual.blocks.29.mlp.down_proj",
|
||||
"visual.blocks.30.attn.qkv",
|
||||
"visual.blocks.30.attn.proj",
|
||||
"visual.blocks.30.mlp.gate_proj",
|
||||
"visual.blocks.30.mlp.up_proj",
|
||||
"visual.blocks.30.mlp.down_proj",
|
||||
"visual.blocks.31.attn.qkv",
|
||||
"visual.blocks.31.attn.proj",
|
||||
"visual.blocks.31.mlp.gate_proj",
|
||||
"visual.blocks.31.mlp.up_proj",
|
||||
"visual.blocks.31.mlp.down_proj",
|
||||
"visual.merger.mlp.0",
|
||||
"visual.merger.mlp.2",
|
||||
"lm_head"
|
||||
],
|
||||
"kv_cache_scheme": null,
|
||||
"quant_method": "compressed-tensors",
|
||||
"quantization_status": "compressed"
|
||||
},
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"intermediate_size": 3420,
|
||||
"num_heads": 16,
|
||||
"in_chans": 3,
|
||||
"out_hidden_size": 2048,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"window_size": 112,
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"tokens_per_second": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"rope_scaling": {
|
||||
"type": "mrope",
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
]
|
||||
},
|
||||
"vocab_size": 151936
|
||||
}
|
||||
Reference in New Issue
Block a user