Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +5 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_0.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_1.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_2.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_3.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_4.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_5.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_6.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_7.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/added_tokens.json +24 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/config.json +31 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/merges.txt +0 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/special_tokens_map.json +31 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/tokenizer.json +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/tokenizer_config.json +208 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/vocab.json +0 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_0.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_1.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_2.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_3.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_4.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_5.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_6.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_7.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_0.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_1.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_2.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_3.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_4.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_5.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_6.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_7.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/data.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_0.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_1.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_2.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_3.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_4.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_5.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_6.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_7.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/added_tokens.json +24 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/config.json +31 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/merges.txt +0 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/special_tokens_map.json +31 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/tokenizer.json +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/tokenizer_config.json +208 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/vocab.json +0 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/model_world_size_8_rank_0.pt +3 -0
- es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/model_world_size_8_rank_1.pt +3 -0
.gitattributes
CHANGED
@@ -70,3 +70,8 @@ es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_2400/act
|
|
70 |
es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_3200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
71 |
es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_4000/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
72 |
es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_4800/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
70 |
es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_3200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
71 |
es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_4000/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
72 |
es-qwen-math-base-7b-3k-stage2-6k-t0-ds_o2_aug-kl0.01-debug/global_step_4800/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
73 |
+
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
74 |
+
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
75 |
+
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
76 |
+
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_400_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
77 |
+
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3deee528d41587decc0f3adf0a10fd20a66ddf9ba1dca907acba0982b5a8e67e
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a32b2a2e325593f1b112e5ade97cf71f7550dc701d63ad7486df77b2435cd6
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9235a6f81dc68c370dc806a6bfadead4e1b5bb4b4ad1890bd92a69774bc8b124
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40af7dde6a7c769a56546c7c5f4b77d0f1c01f10e3d407d83ba765feeabbb88a
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_4.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1bc287b562debe8d3d8ad03d58ebb2a0dc7765b64cf2bc28359dec43bba2d3b
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_5.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d186d97a6c6b7eac0f912499e2181d099cc96741518a8499feedef50436d2301
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_6.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:379b7c2a102af27da0b194e6d2e80e5aa7e8a3c59eb53b77f4df4387ced12d95
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/extra_state_world_size_8_rank_7.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce95e807458c6f4732014b29eff7ed2f5ba478a91d56d026539a4cec7487815
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "/export/xgen-small/efficientscaling/checkpoints/es/es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2000_hf",
|
4 |
+
"architectures": [
|
5 |
+
"Qwen2ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 28,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"pad_token_id": 151643,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000,
|
23 |
+
"sliding_window": 4096,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.49.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"use_mrope": false,
|
29 |
+
"use_sliding_window": false,
|
30 |
+
"vocab_size": 152064
|
31 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|endoftext|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/huggingface/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e808518cad1522e64c82ae2f548e576a7442fac1a753b9f9dc5c0b643e09929
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dd1d37a3542f146e669b6cfa5388052f3900b58437c26c3def162096772c5ef
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ff4829893142654887f48f414c860d9ff8bdcb18c95ba7bac8177ec1d17262b
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a496242fef35e617e8c0beabc915caf113d5f6fe557c2ffb3a7ef53b05ee34b
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_4.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9324b35e1014cc373afa9bdf61751af3b45fb745bfd433751df959943b2b25f
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_5.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5dadf6067309a686be06e215f943fe7e0df86a0eff66ced5d0bd687bb9ff052
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_6.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2baa7eccbcfeb7036e69e92e04421ca7536d383265e14f9c7d5a9019366be8
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/model_world_size_8_rank_7.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce6e3faf239bf3ff00b9a97ea001c252badafd0e82c4c5bc913c714d0b83fbd2
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83b22ca394e51e3d2cc0f8599927eeea33f17e5ec2e0a8a086f5c4e9583ef29e
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d318424285481e701953a3b6c53583df8df48724bb48f24d72a5faaffe30038d
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7f69e3bc6be769971fcdc76d347e2c4c665b8fd04b81ac312d147d494021b7b
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:108f7b5eac5f9dd415e01ceece517ce36b3fca1e8a0a49d63efae963dba6feab
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_4.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5146994315f4e673cc7ff8d309eb025c1c1bcd1e9ac161304954ce2ea3148477
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_5.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82eb880509b62f382b89e749a8ab5a8d7aeb2753bb018d6838278c28d5377144
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_6.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08adcf64a02a7870b035a3b6335dbee3b3e91e7cd28865fc1c44e1d2840aad0a
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/actor/optim_world_size_8_rank_7.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2039aeda15929a70cc3671682e4d7a5fff3367d7a5e2434a6049dbc02ddd686b
|
3 |
+
size 7615643215
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_160/data.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3af9983e3037f819adb7b2b8c9e6594c2f81d265dc18d510fa2223bed0fa0992
|
3 |
+
size 6948621
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2697e1c4b0c34f30e566bfc11c585bfdb091b5d4bddc5227617826c04a9524e2
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae79dd5238b9056fb4b02d7c0863f3a490e6a5de1dec4cfbc1124b6ccecd9aa4
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_2.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c3c6ba90a96160cd9c1c2facf97d930b32fdfd294df1daebb0df1bb8bcc6a64
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_3.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cad98abbbf1617704308ad47e9876e590f953bf6ceb34403ca2390edf426546
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_4.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86bc459b3d86a30c042b5e9398abe5c10ab55bff7be69a6a5c5c786ce1cfd209
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_5.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf69ee230ea586c9e697728dd9dc5fd5c8f4c6e799736bf33d283e8978d787c0
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_6.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:148de62cad84afa264eabd29d299c771cd578ea0e6d3e2d4ec3889be943828ba
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/extra_state_world_size_8_rank_7.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55477ed987298e03dbeb95c2379dce4d80b69684f0428ba6803bf6cb9d027b40
|
3 |
+
size 14632
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "/export/xgen-small/efficientscaling/checkpoints/es/es-qwen-math-base-7b-3k-40k-ds_o2/global_step_2000_hf",
|
4 |
+
"architectures": [
|
5 |
+
"Qwen2ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 28,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"pad_token_id": 151643,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000,
|
23 |
+
"sliding_window": 4096,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.49.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"use_mrope": false,
|
29 |
+
"use_sliding_window": false,
|
30 |
+
"vocab_size": 152064
|
31 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|endoftext|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/huggingface/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/model_world_size_8_rank_0.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdcbadefe4bc8ba0c6461798a343614fc0e4ff1a42b9c907d687ac62bb29e285
|
3 |
+
size 3807995194
|
es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2/global_step_240/actor/model_world_size_8_rank_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ee573184abcfb6f222b26b522d8908f9a0aff6b86bfe5d007e422aa6ddac47a
|
3 |
+
size 3807995194
|