Upload folder using huggingface_hub

.gitattributes

@@ -57,3 +57,4 @@ planning_2509_DeepSeek-R1-Distill-Qwen-1.5B_lbr_bf_grpo/actor/tokenizer.json fil
 planning_2509_DeepSeek-R1-Distill-Qwen-7B_bf_grpo/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 planning_2509_DeepSeek-R1-Distill-Qwen-7B_lbr_bf_grpo/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 planning_2509_DeepSeek-R1-Distill-Qwen-7B_lbr_grpo/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "dtype": "float32",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff6e688c1b18085aefbbc58c90b5554b832f2706947d26f91a3c81f7ea3b823
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f8a890de3f9cf014179947736a39d30331f356118a6056fe767ef0a4e77b1e
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa4ee31d0541deb0640b617bbf935afd4a2fd3aab023b4a29de948c16db2a3a
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fd8342441099a4e82139d5f96033d65e781f77d6c599d7d6bd608be7815e1a
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8206ef0d8b46bd4d7793e07471065a697f94f00305dd34fecda05be0177a64a
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fae6228f58cb01cc537669a80fd4eca91b4eafc82ffe620b8d4478fba44e16
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8e21474c635697c4ae6fc47915d7a6565a2df36ecfe7859a6818a8ad474b43
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/extra_state_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527f6447be541452ac185245abafbaf1d6a152a3e5eb4712f2ac12f8238fa57d
+size 15077

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.57.0"
+}

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1ad4b22a63d5755cf75078d2f5861c64897c0642df144457e2c642fb6209d4
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7984bed8b0a37bcefa76749723614a1da90eebb06a591b45d4da1ea0249802b3
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389ec52811ba752ca505450a03e3fb5f44e8014f9f83fd5abd04265ba16d06b9
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edadf77107d6aff533903bbe2e08e9b991e947b232e42ff206867d7a0e512c0d
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9d39ab3a766992f29a6a88e613e9d89110f2b7f37946ec7e5fb33dde5a5d8b
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b05f06cd3d15df76207afa689c4c2c88e11c709df1138800d9c68ee94ca807e
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24fe07d1b5ea5d37475f3b586d971e81802d0d7bd75f652baa88312f3a0af4b
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/model_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993b9c90447ab3553cbf1d7f9dd3e4d171953d532e7980a75269a102e8d54aa7
+size 3807995563

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebc1e70f5997f1ad3d48f64d6751ffeb7d06f92c47ff187b9c1db90f6a2544f
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da54f59f97095c6bf74488dab0bb51b28213b8894aa2acf831b97742c1b04934
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7bbd6bc1e834ff9e99a350405e939ff322f84bdbe4caf9bab083a87a4589da
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80882df83469ad93eddd6d0cf2cb2dbc92785822daaae0c59e883fbec5140f0
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542076fdd23c9ec3349be00cf930b6b7fec6e8af1a83ed621bab0150a6e841ac
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33803f852de6a1a5e90c9bea74452835227fdfa379472fa567843f18e1e78372
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b36df1471994b22f9e8ac6b3d2dafed46523b8a07ddbb708d3fd0173b93cdb4
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/optim_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6de4145ae229ae77fabac8ad7c293795d9086c2911f8a7abe7dd0771ffac10
+size 7615642880

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/actor/tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

math_2509_DeepSeek-R1-Distill-Qwen-7B_grpo/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245148ec931315173a8bfed7878c44b2ed50b386196648215327aacd894509f5
+size 1947