Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/chat_template.jinja +1 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/config.json +178 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/generation_config.json +13 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/latest +1 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/model-00001-of-00002.safetensors +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/model-00002-of-00002.safetensors +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/model.safetensors.index.json +0 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/processor_config.json +75 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_0.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_1.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_10.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_11.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_12.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_13.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_14.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_15.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_16.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_17.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_18.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_19.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_2.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_20.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_21.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_22.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_23.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_24.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_25.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_26.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_27.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_28.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_29.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_3.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_30.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_31.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_32.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_33.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_34.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_35.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_36.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_37.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_38.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_39.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_4.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_40.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_41.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_42.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_43.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_44.pth +3 -0
- g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_45.pth +3 -0
.gitattributes
CHANGED
|
@@ -86,3 +86,4 @@ g2_6_oldcode_review_newcode_v4/pre-anneal/500M/tokenizer.json filter=lfs diff=lf
|
|
| 86 |
g2_5_plan_newcode__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 87 |
g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 88 |
g2_6_oldcode_review_newcode_v4__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 86 |
g2_5_plan_newcode__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 87 |
g2_6_oldcode_review_newcode_v4__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 88 |
g2_6_oldcode_review_newcode_v4__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
g1_0_baseline_original_code__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
g1_0_baseline_original_code__edit/pre-anneal/500M/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '<eos>' }}{% endif %}{% endfor %}
|
g1_0_baseline_original_code__edit/pre-anneal/500M/config.json
ADDED
|
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": null,
|
| 6 |
+
"audio_token_id": 258881,
|
| 7 |
+
"boa_token_id": 256000,
|
| 8 |
+
"boi_token_id": 255999,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eoa_token_id": 258883,
|
| 12 |
+
"eoa_token_index": 258883,
|
| 13 |
+
"eoi_token_id": 258882,
|
| 14 |
+
"eos_token_id": 1,
|
| 15 |
+
"hidden_size": 5376,
|
| 16 |
+
"image_token_id": 258880,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"model_type": "gemma4",
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"text_config": {
|
| 21 |
+
"attention_bias": false,
|
| 22 |
+
"attention_dropout": 0.0,
|
| 23 |
+
"attention_k_eq_v": true,
|
| 24 |
+
"bos_token_id": 2,
|
| 25 |
+
"dtype": "bfloat16",
|
| 26 |
+
"enable_moe_block": false,
|
| 27 |
+
"eos_token_id": 1,
|
| 28 |
+
"expert_intermediate_size": null,
|
| 29 |
+
"final_logit_softcapping": 30.0,
|
| 30 |
+
"global_head_dim": 512,
|
| 31 |
+
"head_dim": 256,
|
| 32 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 33 |
+
"hidden_size": 5376,
|
| 34 |
+
"hidden_size_per_layer_input": 0,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 21504,
|
| 37 |
+
"layer_types": [
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"sliding_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"sliding_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"sliding_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"sliding_attention",
|
| 72 |
+
"sliding_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"sliding_attention",
|
| 75 |
+
"sliding_attention",
|
| 76 |
+
"sliding_attention",
|
| 77 |
+
"sliding_attention",
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"sliding_attention",
|
| 81 |
+
"sliding_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"sliding_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"sliding_attention",
|
| 87 |
+
"sliding_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"sliding_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"full_attention",
|
| 92 |
+
"sliding_attention",
|
| 93 |
+
"sliding_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"sliding_attention",
|
| 96 |
+
"sliding_attention",
|
| 97 |
+
"full_attention"
|
| 98 |
+
],
|
| 99 |
+
"max_position_embeddings": 262144,
|
| 100 |
+
"model_type": "gemma4_text",
|
| 101 |
+
"moe_intermediate_size": null,
|
| 102 |
+
"num_attention_heads": 32,
|
| 103 |
+
"num_experts": null,
|
| 104 |
+
"num_global_key_value_heads": 4,
|
| 105 |
+
"num_hidden_layers": 60,
|
| 106 |
+
"num_key_value_heads": 16,
|
| 107 |
+
"num_kv_shared_layers": 0,
|
| 108 |
+
"pad_token_id": 0,
|
| 109 |
+
"rms_norm_eps": 1e-06,
|
| 110 |
+
"rope_parameters": {
|
| 111 |
+
"full_attention": {
|
| 112 |
+
"partial_rotary_factor": 0.25,
|
| 113 |
+
"rope_theta": 1000000.0,
|
| 114 |
+
"rope_type": "proportional"
|
| 115 |
+
},
|
| 116 |
+
"sliding_attention": {
|
| 117 |
+
"rope_theta": 10000.0,
|
| 118 |
+
"rope_type": "default"
|
| 119 |
+
}
|
| 120 |
+
},
|
| 121 |
+
"sliding_window": 1024,
|
| 122 |
+
"tie_word_embeddings": true,
|
| 123 |
+
"top_k_experts": null,
|
| 124 |
+
"use_bidirectional_attention": "vision",
|
| 125 |
+
"use_cache": false,
|
| 126 |
+
"use_double_wide_mlp": false,
|
| 127 |
+
"vocab_size": 262144,
|
| 128 |
+
"vocab_size_per_layer_input": 262144
|
| 129 |
+
},
|
| 130 |
+
"tie_word_embeddings": true,
|
| 131 |
+
"transformers_version": "5.10.0",
|
| 132 |
+
"use_cache": false,
|
| 133 |
+
"video_token_id": 258884,
|
| 134 |
+
"vision_config": {
|
| 135 |
+
"_name_or_path": "",
|
| 136 |
+
"architectures": null,
|
| 137 |
+
"attention_bias": false,
|
| 138 |
+
"attention_dropout": 0.0,
|
| 139 |
+
"chunk_size_feed_forward": 0,
|
| 140 |
+
"default_output_length": 280,
|
| 141 |
+
"dtype": "bfloat16",
|
| 142 |
+
"global_head_dim": 72,
|
| 143 |
+
"head_dim": 72,
|
| 144 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 145 |
+
"hidden_size": 1152,
|
| 146 |
+
"id2label": {
|
| 147 |
+
"0": "LABEL_0",
|
| 148 |
+
"1": "LABEL_1"
|
| 149 |
+
},
|
| 150 |
+
"initializer_range": 0.02,
|
| 151 |
+
"intermediate_size": 4304,
|
| 152 |
+
"is_encoder_decoder": false,
|
| 153 |
+
"label2id": {
|
| 154 |
+
"LABEL_0": 0,
|
| 155 |
+
"LABEL_1": 1
|
| 156 |
+
},
|
| 157 |
+
"max_position_embeddings": 131072,
|
| 158 |
+
"model_type": "gemma4_vision",
|
| 159 |
+
"num_attention_heads": 16,
|
| 160 |
+
"num_hidden_layers": 27,
|
| 161 |
+
"num_key_value_heads": 16,
|
| 162 |
+
"output_attentions": false,
|
| 163 |
+
"output_hidden_states": false,
|
| 164 |
+
"patch_size": 16,
|
| 165 |
+
"pooling_kernel_size": 3,
|
| 166 |
+
"position_embedding_size": 10240,
|
| 167 |
+
"problem_type": null,
|
| 168 |
+
"return_dict": true,
|
| 169 |
+
"rms_norm_eps": 1e-06,
|
| 170 |
+
"rope_parameters": {
|
| 171 |
+
"rope_theta": 100.0,
|
| 172 |
+
"rope_type": "default"
|
| 173 |
+
},
|
| 174 |
+
"standardize": true,
|
| 175 |
+
"use_clipped_linears": false
|
| 176 |
+
},
|
| 177 |
+
"vision_soft_tokens_per_image": 280
|
| 178 |
+
}
|
g1_0_baseline_original_code__edit/pre-anneal/500M/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
1
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.10.0"
|
| 13 |
+
}
|
g1_0_baseline_original_code__edit/pre-anneal/500M/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step636
|
g1_0_baseline_original_code__edit/pre-anneal/500M/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4ff7e61c76864e4f4640b5499f38e14cd8ed87dd674035bef7d3cab42104847
|
| 3 |
+
size 49923154850
|
g1_0_baseline_original_code__edit/pre-anneal/500M/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:469465d56e9e7364eccb473f676426e5a3141f5fdf45a7d66f39aa435698236c
|
| 3 |
+
size 12623183414
|
g1_0_baseline_original_code__edit/pre-anneal/500M/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
g1_0_baseline_original_code__edit/pre-anneal/500M/processor_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 7 |
+
"feature_size": 128,
|
| 8 |
+
"fft_length": 512,
|
| 9 |
+
"fft_overdrive": false,
|
| 10 |
+
"frame_length": 320,
|
| 11 |
+
"hop_length": 160,
|
| 12 |
+
"input_scale_factor": 1.0,
|
| 13 |
+
"max_frequency": 8000.0,
|
| 14 |
+
"mel_floor": 0.001,
|
| 15 |
+
"min_frequency": 0.0,
|
| 16 |
+
"padding_side": "right",
|
| 17 |
+
"padding_value": 0.0,
|
| 18 |
+
"per_bin_mean": null,
|
| 19 |
+
"per_bin_stddev": null,
|
| 20 |
+
"preemphasis": 0.0,
|
| 21 |
+
"preemphasis_htk_flavor": true,
|
| 22 |
+
"return_attention_mask": true,
|
| 23 |
+
"sampling_rate": 16000
|
| 24 |
+
},
|
| 25 |
+
"image_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": false,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"do_resize": true,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0
|
| 34 |
+
],
|
| 35 |
+
"image_processor_type": "Gemma4ImageProcessor",
|
| 36 |
+
"image_seq_length": 280,
|
| 37 |
+
"image_std": [
|
| 38 |
+
1.0,
|
| 39 |
+
1.0,
|
| 40 |
+
1.0
|
| 41 |
+
],
|
| 42 |
+
"max_soft_tokens": 280,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pooling_kernel_size": 3,
|
| 45 |
+
"resample": 3,
|
| 46 |
+
"rescale_factor": 0.00392156862745098
|
| 47 |
+
},
|
| 48 |
+
"image_seq_length": 280,
|
| 49 |
+
"processor_class": "Gemma4Processor",
|
| 50 |
+
"video_processor": {
|
| 51 |
+
"do_convert_rgb": true,
|
| 52 |
+
"do_normalize": true,
|
| 53 |
+
"do_rescale": true,
|
| 54 |
+
"do_resize": true,
|
| 55 |
+
"do_sample_frames": true,
|
| 56 |
+
"image_mean": [
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0
|
| 60 |
+
],
|
| 61 |
+
"image_std": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"max_soft_tokens": 70,
|
| 67 |
+
"num_frames": 32,
|
| 68 |
+
"patch_size": 16,
|
| 69 |
+
"pooling_kernel_size": 3,
|
| 70 |
+
"resample": 3,
|
| 71 |
+
"rescale_factor": 0.00392156862745098,
|
| 72 |
+
"return_metadata": false,
|
| 73 |
+
"video_processor_type": "Gemma4VideoProcessor"
|
| 74 |
+
}
|
| 75 |
+
}
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d7dcf54a8dbd1fff243640ddc034149fbe7c90ed70b8a95a6bb093e989a7577
|
| 3 |
+
size 14469
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a2b0b9d330140afd742a57df45106276d425d38a78e53b0fd43dba9559f8d4
|
| 3 |
+
size 14469
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_10.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ce222f8f11fd62fd6cb82264500aefbc9e7ef16907ed3e4aa3a8a99c21d95d3
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_11.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d07144bfc4ed675dda70ab66923d17d6f9233560b2db09689cbe1f262c590c88
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_12.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6e08d78f1863585829c3beb514b0be2b6dd5058d44950b2f5529180ed3bf200
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_13.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd02cc08e60bd490e7809bb22626bbc382309e0548b8d176712a72282b79bc7
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_14.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44d37c4ee644f088f47b9557f56e86307d31179db8414f7bddc801e9db40814e
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_15.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a61612e6aea130f0a379adbe720ad1b2bf382caaf91aaabbe6692f9b6842cfd7
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_16.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:048535719240855c8721c08701459b3772c42c064b43cefb8c0859c8c8847bfb
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_17.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b381294da5be4f5d6c1fff6daed9292ef379337e249c8925ef46b492ef3ee310
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_18.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ebc632331f136fb796e109f7d0378641d1e5aadd801c90aff7d8bf2598d0e13
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_19.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbbbc31fd3a5dc41a109296b8e8462fa1e9a5f271dff0ac41dd90f8e4d2d7c36
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5db634f6ed5151d3c898fbe3c365f950516c404bed926de16b253b26e63c7cf
|
| 3 |
+
size 14469
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_20.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e0128907c3a7a5f8d28de699f336992dcbbe4936f86e3a5ee90f2dec42e79f
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_21.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22597879b2fe99eba1397996a6ccc3e1ef32321f02c63d8158971b41a70fb8e8
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_22.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38c34c34cb1f037aabc2706908c5d7212ed45922130afce933667e1454b6f034
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_23.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9269652b84f705adc87d3a16df047010fb3fa29b11349033478b4776d15f0e32
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_24.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a9e6a074c879eb7683ab1cca4f686aab7505f734596e8bf42e3582aff414cc5
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_25.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:addb12b2fe7960526e1e7786804e1359c161bb40e8c305f708dc0cc14061bff2
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_26.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c744753a5acb3e37d956b8f7eb68d2cca0f195c1d0389c146cc8e2d00736bb4
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_27.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b586c343d320258372038d4d211ed449c11517e9f5e1c5fcb76bfc7a74687fb
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_28.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b46e1a86fdd08125a5abc42a2d4618d55acd88300e9cf35abb586e4d534eea9
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_29.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef12a2de484b1fb274fd5576d9ac18c80f0659ad29a92c43d8e90fdd70a7734f
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad774eade44525098fff2d5910e3d16565fca4c2af29ed0bc4d9315a8ac9607a
|
| 3 |
+
size 14469
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_30.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5a64f55f5b524c1d45986d113944687207fd40932aa517c50ac25554d380cb
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_31.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3c2549059d0e017510a8912ae3114b8312b83d6a0cecc341356570eb3bbbe66
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_32.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7879edbf3c49cb48dbb9dd713c7c546507031ed29db3b17a4e0566464395b40
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_33.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f72e27887b2cd13b128841aff5988a61d290f09a99374194b72d970e50b061a9
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_34.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb31c31655e2888adededf783d31f622880ad5d94d3482d6513222056b02afee
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_35.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fbefc809d13afc0266f26eee722ed2215ccbf20ea993393930075bc8e755758
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_36.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c94c0223ead01438d94c0512a52285243eae170c3762b1074dc3d903e6695cc
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_37.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52b9758407564a28dadafc20701dfacd7e5a298a669158c72a1dbd5bf49ecbca
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_38.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77138dd39b3982453c2e48495f87c54612996f42f004a82b51d977de9b594c20
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_39.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fc0038ae4a11c965bc71937b7211bdf963b37b588f440aa7bf0bf1b41d8e89
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebdee1b37be2238764bcfeed9dad268e938248152b0fba60eaf89adda99eac0f
|
| 3 |
+
size 14469
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_40.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a2b4624c04df7281c4f6a2322c5590dd34e8e99bf279eb95068c2a044bacbdb
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_41.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eccb0c6a383aa75920dc3d0dd931477746e472d1dfc8bed5d67053d53cc50cbf
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_42.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:526e100a2d0659e72a19bb503ea5a1ea901df362ae751f70ee167c8bacb755ae
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_43.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3049597adee88bd5adaae1a41905e21082bdcc322e02b9b49658766371dcd567
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_44.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79b20c147d255aee4a21cc00ce71f9395c14749ba61cd83fa0f8eb2b5efa380a
|
| 3 |
+
size 14476
|
g1_0_baseline_original_code__edit/pre-anneal/500M/rng_state_45.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b12c2ace72a2f50d02eca5766de8929307316f6416cd40e9094152c62d12542
|
| 3 |
+
size 14476
|