Delete .ipynb_checkpoints
Browse files
.ipynb_checkpoints/config-checkpoint.json
DELETED
@@ -1,85 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"name_or_path": "tclf90/GLM-4.5V-AWQ",
|
3 |
-
"architectures": [
|
4 |
-
"Glm4vMoeForConditionalGeneration"
|
5 |
-
],
|
6 |
-
"model_type": "glm4v_moe",
|
7 |
-
"text_config": {
|
8 |
-
"pad_token_id": 151329,
|
9 |
-
"vocab_size": 151552,
|
10 |
-
"eos_token_id": [
|
11 |
-
151329,
|
12 |
-
151336,
|
13 |
-
151338
|
14 |
-
],
|
15 |
-
"image_end_token_id": 151340,
|
16 |
-
"image_start_token_id": 151339,
|
17 |
-
"image_token_id": 151363,
|
18 |
-
"head_dim": 128,
|
19 |
-
"attention_bias": true,
|
20 |
-
"attention_dropout": 0.0,
|
21 |
-
"first_k_dense_replace": 1,
|
22 |
-
"hidden_act": "silu",
|
23 |
-
"hidden_size": 4096,
|
24 |
-
"initializer_range": 0.02,
|
25 |
-
"intermediate_size": 11264,
|
26 |
-
"max_position_embeddings": 65536,
|
27 |
-
"model_type": "glm4v_moe_text",
|
28 |
-
"moe_intermediate_size": 1408,
|
29 |
-
"n_group": 1,
|
30 |
-
"n_routed_experts": 128,
|
31 |
-
"n_shared_experts": 1,
|
32 |
-
"norm_topk_prob": true,
|
33 |
-
"num_attention_heads": 96,
|
34 |
-
"num_experts_per_tok": 8,
|
35 |
-
"num_hidden_layers": 46,
|
36 |
-
"num_key_value_heads": 8,
|
37 |
-
"partial_rotary_factor": 0.5,
|
38 |
-
"rms_norm_eps": 1e-05,
|
39 |
-
"torch_dtype": "bfloat16",
|
40 |
-
"rope_scaling": {
|
41 |
-
"rope_type": "default",
|
42 |
-
"mrope_section": [
|
43 |
-
8,
|
44 |
-
12,
|
45 |
-
12
|
46 |
-
]
|
47 |
-
},
|
48 |
-
"rope_theta": 10000.0,
|
49 |
-
"routed_scaling_factor": 1.0,
|
50 |
-
"topk_group": 1,
|
51 |
-
"use_cache": true,
|
52 |
-
"use_qk_norm": false
|
53 |
-
},
|
54 |
-
"torch_dtype": "float16",
|
55 |
-
"transformers_version": "4.55.0.dev0",
|
56 |
-
"video_end_token_id": 151342,
|
57 |
-
"video_start_token_id": 151341,
|
58 |
-
"video_token_id": 151364,
|
59 |
-
"vision_config": {
|
60 |
-
"attention_bias": false,
|
61 |
-
"attention_dropout": 0.0,
|
62 |
-
"depth": 24,
|
63 |
-
"hidden_act": "silu",
|
64 |
-
"hidden_size": 1536,
|
65 |
-
"image_size": 336,
|
66 |
-
"in_channels": 3,
|
67 |
-
"initializer_range": 0.02,
|
68 |
-
"intermediate_size": 11264,
|
69 |
-
"model_type": "glm4v_moe",
|
70 |
-
"num_heads": 12,
|
71 |
-
"out_hidden_size": 4096,
|
72 |
-
"patch_size": 14,
|
73 |
-
"rms_norm_eps": 1e-05,
|
74 |
-
"spatial_merge_size": 2,
|
75 |
-
"temporal_patch_size": 2
|
76 |
-
},
|
77 |
-
"quantization_config": {
|
78 |
-
"quant_method": "awq_marlin",
|
79 |
-
"bits": 4,
|
80 |
-
"group_size": 128,
|
81 |
-
"version": "gemm",
|
82 |
-
"zero_point": true,
|
83 |
-
"modules_to_not_convert": ["blocks.", "model.embed_tokens", "model.layers.0.mlp.shared_experts.", "model.layers.1.mlp.shared_experts.", "model.layers.2.mlp.shared_experts.", "model.layers.3.mlp.shared_experts.", "model.layers.4.mlp.shared_experts.", "model.layers.5.mlp.shared_experts.", "model.layers.6.mlp.shared_experts.", "model.layers.7.mlp.shared_experts.", "model.layers.8.mlp.shared_experts.", "model.layers.9.mlp.shared_experts.", "model.layers.10.mlp.shared_experts.", "model.layers.11.mlp.shared_experts.", "model.layers.12.mlp.shared_experts.", "model.layers.13.mlp.shared_experts.", "model.layers.14.mlp.shared_experts.", "model.layers.15.mlp.shared_experts.", "model.layers.16.mlp.shared_experts.", "model.layers.17.mlp.shared_experts.", "model.layers.18.mlp.shared_experts.", "model.layers.19.mlp.shared_experts.", "model.layers.20.mlp.shared_experts.", "model.layers.21.mlp.shared_experts.", "model.layers.22.mlp.shared_experts.", "model.layers.23.mlp.shared_experts.", "model.layers.24.mlp.shared_experts.", "model.layers.25.mlp.shared_experts.", "model.layers.26.mlp.shared_experts.", "model.layers.27.mlp.shared_experts.", "model.layers.28.mlp.shared_experts.", "model.layers.29.mlp.shared_experts.", "model.layers.30.mlp.shared_experts.", "model.layers.31.mlp.shared_experts.", "model.layers.32.mlp.shared_experts.", "model.layers.33.mlp.shared_experts.", "model.layers.34.mlp.shared_experts.", "model.layers.35.mlp.shared_experts.", "model.layers.36.mlp.shared_experts.", "model.layers.37.mlp.shared_experts.", "model.layers.38.mlp.shared_experts.", "model.layers.39.mlp.shared_experts.", "model.layers.40.mlp.shared_experts.", "model.layers.41.mlp.shared_experts.", "model.layers.42.mlp.shared_experts.", "model.layers.43.mlp.shared_experts.", "model.layers.44.mlp.shared_experts.", "model.layers.45.mlp.shared_experts.", "lm_head"]
|
84 |
-
}
|
85 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/model.safetensors.index-checkpoint.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|