Upload merged LoRA model via merge_lora tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

MERGE_METADATA.json

@@ -0,0 +1,23 @@
+{
+  "base_model": "qwen/Qwen3-235B-A22B",
+  "adapters": [
+    "neko-llm/Qwen3-235B-epoch2"
+  ],
+  "out_dir": "/home/Competition2025/P02/P02U001/llm2025compet/inference/merge_lora/merged/Qwen3-235B-A22B-epoch2-merged",
+  "dtype": "bf16",
+  "device_map": "auto",
+  "offload_dir": "offload/Qwen3-235B-A22B-epoch2",
+  "max_shard_size": "5GB",
+  "revision": null,
+  "trust_remote_code": true,
+  "allow_quantized_merge": false,
+  "save_tokenizer": true,
+  "upload_to_hub": true,
+  "hub_repo_id": "weblab-llm-competition-2025-bridge/neko-prelim-Qwen3-235B-A22B",
+  "hub_private": false,
+  "torch_version": "2.6.0+cu124",
+  "env": {
+    "HF_HUB_ENABLE_HF_TRANSFER": "1",
+    "TRANSFORMERS_OFFLINE": "0"
+  }
+}

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 94,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 1536,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 94,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.3"
+}

model-00001-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ca1a41c59eab49721e21a1902d62a0679e56e75031f4cb009374da862d2e75
+size 4999647472

model-00002-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3b485e31122c14e4165ab2dc16c3df8b68aa9b3c11003da6936b86d5da2966
+size 4988141728

model-00003-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba21c79495efdf28db45c2e38bb8ea117a853c333dedb7da5b527406f9491929
+size 4988141728

model-00004-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7f358f800e64215510da5a8f4769a19308b5afdf98648a33c441118aab20e3
+size 4988141728

model-00005-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2a9ec7420a007c886728e47c2ff382865595d233426c0d03ea001e453e32d7
+size 4988141728

model-00006-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4221adec5425ebd0375349fa662c959a8849a24b70c41197bf1e2ad669af83fe
+size 4988141728

model-00007-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90d568ef25e881fa29ec2e7fbe35dd73f0bd24c6f989fa411f2df057d40a052
+size 4988141728

model-00008-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1480c54ac4258fd9f221bd3acc53e5e8a2ce5935c5290365e5fe7c620e2df8d
+size 4988141728

model-00009-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24bda770f9a9d20cb5501cad547d12be2f020b739b6574775bd7bc725ca4c77
+size 4988141728

model-00010-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394f4f44eaf80779e778d0548aae25a44fba43e3cf10e4b9a2274f9cb0ce45dc
+size 4988141728

model-00011-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef7169a7d9306fbf7d3f79f820f7cb949845057c674beebc5a1a98dcd43c453
+size 4988142048

model-00012-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0d4b08417b79c9a110fc326dd7a0712f82247da001551cccb6462dbec706e9
+size 4988142120

model-00013-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70d16b45c59ec98c9d76aabea7df5354bee804533b6f401488381580ea8e489
+size 4988142120

model-00014-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38584493d9a65f13e22df564522be3e6c3f2192d02699386980b19e0558c9eb
+size 4988142120

model-00015-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2332e100dfc257368f31b73ce6ee2c4a47bd9619e03b2e3c66fce396b32155f
+size 4988142120

model-00016-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef13e20a24527566d07f534612b82ec23f3c376f98beffbaf7a360c2a15cce4d
+size 4988142120

model-00017-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60a844005cc4bf4d37391b94802d4facaebaca6a66f7d617f17ffedd4ba407e
+size 4988142120

model-00018-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2813071636f9142f36456fa4342d93011f2aba2cf9449ede29837cd3490b9f
+size 4988142120

model-00019-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce28647c9de3ba5f85c8caf0425a6e85c120ff7f02d2bd9af5c78cfe935de23
+size 4988142120

model-00020-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ca00e6f51137038eef2efde138db64dd9ca06987da7ba0b042025123f16465
+size 4988142120

model-00021-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363ff0dc84887d9d5a33bdc9b631ed2a4074d3181a3432abe5a64598fc54fd5d
+size 4988142120

model-00022-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076cac7308c143bd6a2a4a97f35ecaa996d1a3dd3203a100b8aa651b164c4ffe
+size 4988142120

model-00023-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f38e2e1ecaf05c1423d8196399a78a2a88e9aff55e9372e610291949d84d3d
+size 4988142120

model-00024-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d920e00c3144cb0081d760e6ff3bce1a629a8f0923371288bf954682f9b86c
+size 4988142120

model-00025-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715ae78f548dbd569f7cfa159b825907df3a5d3b0c158e9543b61c9dce54d807
+size 4988142120

model-00026-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb28f0b781593003bb332c477cb0d519a0c3abbd4eb216c4f1b11c199451edeb
+size 4988142120

model-00027-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a74ad3254784076cc54e446c88d858950c820987077956e64cfa20f22eb36a2
+size 4988142120

model-00028-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7305bb325ec559b2f27913a3651c1703816c3d1d937a6df9e1c2959163a8da11
+size 4988142120

model-00029-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b127a1a0bfc7a0a447c0a5f32d7d90a00ca6bc36617ceba6137e80298a9c7b6
+size 4988142120

model-00030-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7317fc167c0cb3cc412ac02d8e0b02dd99b177b5bb198420d1c21ca2787632
+size 4988142120

model-00031-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7615efb5c6dacb83744816f410280632e08dcb79550b4836dbd3d004d8a843
+size 4988142120

model-00032-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca6b4504ebb18adb377a7babd6aba93bd688a6b715d76ac611b1f75d72ad5dd
+size 4988142120

model-00033-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c8372d08fe0f08c2c8c655f489ff16761de0a0ed047f238b9c5226031733cf
+size 4988142120

model-00034-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46d07939e6dcce369ddca595f1f492c09590eafa7a8e8dc431501045ceb73d5
+size 4988142120

model-00035-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffdeaf588033c60907d7200033bedf078ff30d6d9191941e677b6286860e5087
+size 4988142120

model-00036-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed818292f97edc3487b226e471ddf30bc1031b50f1c3c083670a1d922a0b204
+size 4988142120

model-00037-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bf86ad1cc036a3aecd142e501f464c76153611f98e5e4e30544f1361054fca
+size 4988142120

model-00038-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c873a657bd971a78bb25bfdca0b5b82eb16b29026af98e6813e53190198c137
+size 4988142120

model-00039-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707dc8046b3d3316e212518237241b452242a5c04294699d6547baeb0a118fa6
+size 4988142120

model-00040-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248bcbccc274430443fcbd2cca1d8718dc2cb46d0ba7043e6106d33b699b27b7
+size 4988142120

model-00041-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90b9db5d4571f5ac7ef41687c2e553adc70f0010b85c47e30ecead9d64547db
+size 4988142120

model-00042-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323e4ea4b0d0e07e87c507699e11b0b2b292c04defa21b1eda2b4f30945931da
+size 4988142120

model-00043-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e7f33ef79fba4146671a9dd70508ad91cad3ff0cb5ab6d22ba334f67bce51b
+size 4988142120