Delete qwen2_5_math_7b

qwen2_5_math_7b/limo/checkpoint-1025/added_tokens.json

@@ -1,24 +0,0 @@
-{
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

qwen2_5_math_7b/limo/checkpoint-1025/chat_template.jinja

@@ -1,54 +0,0 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
-    {%- endif %}
-    {{- "\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>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\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" }}
-{%- else %}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
-    {%- else %}
-        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- for message in messages %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
-        {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}

qwen2_5_math_7b/limo/checkpoint-1025/config.json

@@ -1,59 +0,0 @@
-{
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "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": 4096,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0",
-  "use_cache": false,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 152064
-}

qwen2_5_math_7b/limo/checkpoint-1025/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.55.0"
-}

qwen2_5_math_7b/limo/checkpoint-1025/model-00001-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b903698ddedc5d1c93a673b58db7bb30eb1454a1b4a540ae0cbd87adf3ff6f82
-size 4976687216

qwen2_5_math_7b/limo/checkpoint-1025/model-00002-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4027a3d18ecef228d23f0fbf8a1f01404eaf19ee2a3e947bc19bf93624faf724
-size 4778622352

qwen2_5_math_7b/limo/checkpoint-1025/model-00003-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e9d9fb62c93d06cc65e10a8b06ce29a5904326edd2b731a1ad567facf1482182
-size 4932743960

qwen2_5_math_7b/limo/checkpoint-1025/model-00004-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a34918be115f506d216221609089bc7594bb6dd80a059e57dfa94945494255ea
-size 4932743992

qwen2_5_math_7b/limo/checkpoint-1025/model-00005-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6a7411de90b998f83caf75af1aff8326b4bccdedfc6972e822c5f9318245766
-size 4998852296

qwen2_5_math_7b/limo/checkpoint-1025/model-00006-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04ab6a8a50097f3104b1921a4fa8240cd73ebfd4fc040a8cc4366df7d87b55da
-size 3662865184

qwen2_5_math_7b/limo/checkpoint-1025/model-00007-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:79818d4fa5d29f45056f6d709b39ff92c303dfec5e534985a9ef9d78070aa8ad
-size 2179989632

qwen2_5_math_7b/limo/checkpoint-1025/model.safetensors.index.json

@@ -1,347 +0,0 @@
-{
-  "metadata": {
-    "total_parameters": 1903904128,
-    "total_size": 30462466048
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00007-of-00007.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.norm.weight": "model-00006-of-00007.safetensors"
-  }
-}

qwen2_5_math_7b/limo/checkpoint-1025/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
-size 15024

qwen2_5_math_7b/limo/checkpoint-1025/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
-size 15024

qwen2_5_math_7b/limo/checkpoint-1025/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
-size 15024

qwen2_5_math_7b/limo/checkpoint-1025/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
-size 15024

qwen2_5_math_7b/limo/checkpoint-1025/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f248cf8d7232a4d32a1c7a253ea7a98e8d245b7a745ec212e824a40ae88102c3
-size 1064

qwen2_5_math_7b/limo/checkpoint-1025/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

qwen2_5_math_7b/limo/checkpoint-1025/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896

qwen2_5_math_7b/limo/checkpoint-1025/tokenizer_config.json

@@ -1,208 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "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
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

qwen2_5_math_7b/limo/checkpoint-1230/added_tokens.json

@@ -1,24 +0,0 @@
-{
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

qwen2_5_math_7b/limo/checkpoint-1230/chat_template.jinja

@@ -1,54 +0,0 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
-    {%- endif %}
-    {{- "\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>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\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" }}
-{%- else %}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
-    {%- else %}
-        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- for message in messages %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
-        {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}

qwen2_5_math_7b/limo/checkpoint-1230/config.json

@@ -1,59 +0,0 @@
-{
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "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": 4096,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0",
-  "use_cache": false,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 152064
-}

qwen2_5_math_7b/limo/checkpoint-1230/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.55.0"
-}

qwen2_5_math_7b/limo/checkpoint-1230/model-00001-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:05e692f7b18b9240dd1ee326441c02a34e1d0e34933ef2dc2acc6cf9e5571ea8
-size 4976687216

qwen2_5_math_7b/limo/checkpoint-1230/model-00002-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5caef814e5c510069579f18f2f33fc695e91f767e23dc9e7f191dfe5732ffdc7
-size 4778622352

qwen2_5_math_7b/limo/checkpoint-1230/model-00003-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:66aba33d7f28c0451eb38f62a172891f39dcacad542934508ff9aef48eeed0d5
-size 4932743960

qwen2_5_math_7b/limo/checkpoint-1230/model-00004-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2868cd80aa12deed4fbbfa9da00aadf91c5bfb033c1632c596015154a8e8636
-size 4932743992

qwen2_5_math_7b/limo/checkpoint-1230/model-00005-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9248c203b938376b06f8ab17677c79d177e31b09937cc969e37ac300f895634b
-size 4998852296

qwen2_5_math_7b/limo/checkpoint-1230/model-00006-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf2b2082a3dacc7c482f003514be0269d5a2807b39cbcc4232ec982455cdd9aa
-size 3662865184

qwen2_5_math_7b/limo/checkpoint-1230/model-00007-of-00007.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35c0e13f0564d2c57770633c863624e73f01e60073d799cf872df2f8dc2c2c38
-size 2179989632

qwen2_5_math_7b/limo/checkpoint-1230/model.safetensors.index.json

@@ -1,347 +0,0 @@
-{
-  "metadata": {
-    "total_parameters": 1903904128,
-    "total_size": 30462466048
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00007-of-00007.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "model.norm.weight": "model-00006-of-00007.safetensors"
-  }
-}

qwen2_5_math_7b/limo/checkpoint-1230/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
-size 15024

qwen2_5_math_7b/limo/checkpoint-1230/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
-size 15024

qwen2_5_math_7b/limo/checkpoint-1230/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
-size 15024

qwen2_5_math_7b/limo/checkpoint-1230/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
-size 15024

qwen2_5_math_7b/limo/checkpoint-1230/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52f7b535b1edea536614abde861d1ff7ba7967dbe32fcf39458e08c39d5bc336
-size 1064

qwen2_5_math_7b/limo/checkpoint-1230/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

qwen2_5_math_7b/limo/checkpoint-1230/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896

qwen2_5_math_7b/limo/checkpoint-1230/tokenizer_config.json

@@ -1,208 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "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
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

qwen2_5_math_7b/limo/checkpoint-1435/added_tokens.json

@@ -1,24 +0,0 @@
-{
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

qwen2_5_math_7b/limo/checkpoint-1435/chat_template.jinja

@@ -1,54 +0,0 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
-    {%- endif %}
-    {{- "\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>" }}
-    {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
-    {%- endfor %}
-    {{- "\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" }}
-{%- else %}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
-    {%- else %}
-        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- for message in messages %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
-        {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- '}\n</tool_call>' }}
-        {%- endfor %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}

qwen2_5_math_7b/limo/checkpoint-1435/config.json

@@ -1,59 +0,0 @@
-{
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "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": 4096,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0",
-  "use_cache": false,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 152064
-}

qwen2_5_math_7b/limo/checkpoint-1435/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.55.0"
-}