Update config.json
Browse files- config.json +0 -66
config.json
CHANGED
|
@@ -29,72 +29,6 @@
|
|
| 29 |
},
|
| 30 |
"rope_theta": 1000000.0,
|
| 31 |
"sliding_window": 32768,
|
| 32 |
-
"text_config": {
|
| 33 |
-
"_name_or_path": "/home/jeffrey/EasyR1/checkpoints/baselines/qwen2.5_grpo_medium_new_config/global_step_75/actor/huggingface",
|
| 34 |
-
"architectures": [
|
| 35 |
-
"Qwen2_5_VLForConditionalGeneration"
|
| 36 |
-
],
|
| 37 |
-
"attention_dropout": 0.0,
|
| 38 |
-
"dtype": "float32",
|
| 39 |
-
"eos_token_id": 151645,
|
| 40 |
-
"hidden_act": "silu",
|
| 41 |
-
"hidden_size": 3584,
|
| 42 |
-
"initializer_range": 0.02,
|
| 43 |
-
"intermediate_size": 18944,
|
| 44 |
-
"layer_types": [
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"full_attention",
|
| 54 |
-
"full_attention",
|
| 55 |
-
"full_attention",
|
| 56 |
-
"full_attention",
|
| 57 |
-
"full_attention",
|
| 58 |
-
"full_attention",
|
| 59 |
-
"full_attention",
|
| 60 |
-
"full_attention",
|
| 61 |
-
"full_attention",
|
| 62 |
-
"full_attention",
|
| 63 |
-
"full_attention",
|
| 64 |
-
"full_attention",
|
| 65 |
-
"full_attention",
|
| 66 |
-
"full_attention",
|
| 67 |
-
"full_attention",
|
| 68 |
-
"full_attention",
|
| 69 |
-
"full_attention",
|
| 70 |
-
"full_attention",
|
| 71 |
-
"full_attention",
|
| 72 |
-
"full_attention"
|
| 73 |
-
],
|
| 74 |
-
"max_position_embeddings": 128000,
|
| 75 |
-
"max_window_layers": 28,
|
| 76 |
-
"model_type": "qwen2_5_vl_text",
|
| 77 |
-
"num_attention_heads": 28,
|
| 78 |
-
"num_hidden_layers": 28,
|
| 79 |
-
"num_key_value_heads": 4,
|
| 80 |
-
"pad_token_id": 151643,
|
| 81 |
-
"rms_norm_eps": 1e-06,
|
| 82 |
-
"rope_scaling": {
|
| 83 |
-
"mrope_section": [
|
| 84 |
-
16,
|
| 85 |
-
24,
|
| 86 |
-
24
|
| 87 |
-
],
|
| 88 |
-
"rope_type": "default",
|
| 89 |
-
"type": "default"
|
| 90 |
-
},
|
| 91 |
-
"rope_theta": 1000000.0,
|
| 92 |
-
"sliding_window": null,
|
| 93 |
-
"use_cache": true,
|
| 94 |
-
"use_sliding_window": false,
|
| 95 |
-
"vision_token_id": 151654,
|
| 96 |
-
"vocab_size": 152064
|
| 97 |
-
},
|
| 98 |
"tie_word_embeddings": false,
|
| 99 |
"transformers_version": "4.57.1",
|
| 100 |
"use_cache": true,
|
|
|
|
| 29 |
},
|
| 30 |
"rope_theta": 1000000.0,
|
| 31 |
"sliding_window": 32768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"tie_word_embeddings": false,
|
| 33 |
"transformers_version": "4.57.1",
|
| 34 |
"use_cache": true,
|