mirror of
https://www.modelscope.cn/ZhipuAI/GLM-4.1V-9B-Thinking.git
synced 2026-04-02 11:02:56 +08:00
update for new format config of transformers lib / sglang lib
This commit is contained in:
68
config.json
68
config.json
@ -3,38 +3,50 @@
|
|||||||
"Glm4vForConditionalGeneration"
|
"Glm4vForConditionalGeneration"
|
||||||
],
|
],
|
||||||
"model_type": "glm4v",
|
"model_type": "glm4v",
|
||||||
"attention_bias": true,
|
|
||||||
"attention_dropout": 0.0,
|
|
||||||
"pad_token_id": 151329,
|
|
||||||
"eos_token_id": [
|
|
||||||
151329,
|
|
||||||
151336,
|
|
||||||
151338,
|
|
||||||
151348
|
|
||||||
],
|
|
||||||
"image_start_token_id": 151339,
|
"image_start_token_id": 151339,
|
||||||
"image_end_token_id": 151340,
|
"image_end_token_id": 151340,
|
||||||
"video_start_token_id": 151341,
|
"video_start_token_id": 151341,
|
||||||
"video_end_token_id": 151342,
|
"video_end_token_id": 151342,
|
||||||
"image_token_id": 151343,
|
"image_token_id": 151343,
|
||||||
"video_token_id": 151344,
|
"video_token_id": 151344,
|
||||||
"hidden_act": "silu",
|
|
||||||
"hidden_size": 4096,
|
|
||||||
"initializer_range": 0.02,
|
|
||||||
"intermediate_size": 13696,
|
|
||||||
"max_position_embeddings": 65536,
|
|
||||||
"num_attention_heads": 32,
|
|
||||||
"num_hidden_layers": 40,
|
|
||||||
"num_key_value_heads": 2,
|
|
||||||
"rms_norm_eps": 1e-05,
|
|
||||||
"rope_theta": 10000.0,
|
|
||||||
"tie_word_embeddings": false,
|
"tie_word_embeddings": false,
|
||||||
"torch_dtype": "bfloat16",
|
"transformers_version": "4.57.1",
|
||||||
"transformers_version": "4.53.0dev",
|
"text_config": {
|
||||||
"use_cache": true,
|
"model_type": "glm4v_text",
|
||||||
"vocab_size": 151552,
|
"attention_bias": true,
|
||||||
"partial_rotary_factor": 0.5,
|
"attention_dropout": 0.0,
|
||||||
|
"pad_token_id": 151329,
|
||||||
|
"eos_token_id": [
|
||||||
|
151329,
|
||||||
|
151336,
|
||||||
|
151338,
|
||||||
|
151348
|
||||||
|
],
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 13696,
|
||||||
|
"max_position_embeddings": 65536,
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 151552,
|
||||||
|
"partial_rotary_factor": 0.5,
|
||||||
|
"rope_theta": 10000,
|
||||||
|
"rope_scaling": {
|
||||||
|
"rope_type": "default",
|
||||||
|
"mrope_section": [
|
||||||
|
8,
|
||||||
|
12,
|
||||||
|
12
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
"vision_config": {
|
"vision_config": {
|
||||||
|
"model_type": "glm4v",
|
||||||
"hidden_size": 1536,
|
"hidden_size": 1536,
|
||||||
"depth": 24,
|
"depth": 24,
|
||||||
"num_heads": 12,
|
"num_heads": 12,
|
||||||
@ -49,13 +61,5 @@
|
|||||||
"rms_norm_eps": 1e-05,
|
"rms_norm_eps": 1e-05,
|
||||||
"spatial_merge_size": 2,
|
"spatial_merge_size": 2,
|
||||||
"temporal_patch_size": 2
|
"temporal_patch_size": 2
|
||||||
},
|
|
||||||
"rope_scaling": {
|
|
||||||
"type": "default",
|
|
||||||
"mrope_section": [
|
|
||||||
8,
|
|
||||||
12,
|
|
||||||
12
|
|
||||||
]
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@ -11,5 +11,5 @@
|
|||||||
"top_p": 0.6,
|
"top_p": 0.6,
|
||||||
"temperature": 0.8,
|
"temperature": 0.8,
|
||||||
"top_k": 2,
|
"top_k": 2,
|
||||||
"transformers_version": "4.53.0dev"
|
"transformers_version": "4.57.1"
|
||||||
}
|
}
|
||||||
Reference in New Issue
Block a user