Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,17 @@ 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
+cpt_train_dataset.json filter=lfs diff=lfs merge=lfs -text
+cpt_train_dataset_shard_0.json filter=lfs diff=lfs merge=lfs -text
+cpt_train_dataset_shard_1.json filter=lfs diff=lfs merge=lfs -text
+cpt_train_dataset_shard_2.json filter=lfs diff=lfs merge=lfs -text
+cpt_train_dataset_shard_3.json filter=lfs diff=lfs merge=lfs -text
+cpt_train_dataset_shard_4.json filter=lfs diff=lfs merge=lfs -text
+merged_tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+raw_corpus_hil.txt filter=lfs diff=lfs merge=lfs -text
+sft_train_dataset.json filter=lfs diff=lfs merge=lfs -text
+sft_train_dataset_shard_0.json filter=lfs diff=lfs merge=lfs -text
+sft_train_dataset_shard_1.json filter=lfs diff=lfs merge=lfs -text
+sft_train_dataset_shard_2.json filter=lfs diff=lfs merge=lfs -text
+sft_train_dataset_shard_3.json filter=lfs diff=lfs merge=lfs -text
+sft_train_dataset_shard_4.json filter=lfs diff=lfs merge=lfs -text

cpt_train_dataset.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cebeb5b7093b4f1b7d01566aa8321e4bf7b01422d8748125fb4cd4f6227d5f
+size 87234819

cpt_train_dataset_shard_0.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b07377423eda2e695146c3b364f4aed74eff053b9871a121effbb3b8d1ac376
+size 17510861

cpt_train_dataset_shard_1.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d24692b62ea3e266a270c60a4c959a28f661e78b165b601b72d82a1d98fede
+size 17472164

cpt_train_dataset_shard_2.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7419d86c431caf8b590f788ac5a2d54d111c8b3a1fb1de6ec39dfb8fb2bb33b8
+size 17392999

cpt_train_dataset_shard_3.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cd9f29491e61b6a5ff800243395b70a3f6448e8ff955db8d69108e9ae26b9c
+size 17278956

cpt_train_dataset_shard_4.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c585484634ae3894b2138ea43d0f15d139f1426969cf7b71cdd7167676c7fd2f
+size 17579839

merged_tokenizer/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

merged_tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579a19f2a07b4e0d9a63f31da1d677f2ea7e0dbf8ade390c18fd812e561848f2
+size 12391006

merged_tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

prep_metadata.json

@@ -0,0 +1,21 @@
+{
+  "assets_dir": "/content/qwen3_outputs/assets",
+  "merged_tokenizer_dir": "/content/qwen3_outputs/assets/merged_tokenizer",
+  "cpt_dataset_file": "/content/qwen3_outputs/assets/cpt_train_dataset.json",
+  "sft_dataset_file": "/content/qwen3_outputs/assets/sft_train_dataset.json",
+  "cpt_shards": [
+    "/content/qwen3_outputs/assets/cpt_train_dataset_shard_0.json",
+    "/content/qwen3_outputs/assets/cpt_train_dataset_shard_1.json",
+    "/content/qwen3_outputs/assets/cpt_train_dataset_shard_2.json",
+    "/content/qwen3_outputs/assets/cpt_train_dataset_shard_3.json",
+    "/content/qwen3_outputs/assets/cpt_train_dataset_shard_4.json"
+  ],
+  "sft_shards": [
+    "/content/qwen3_outputs/assets/sft_train_dataset_shard_0.json",
+    "/content/qwen3_outputs/assets/sft_train_dataset_shard_1.json",
+    "/content/qwen3_outputs/assets/sft_train_dataset_shard_2.json",
+    "/content/qwen3_outputs/assets/sft_train_dataset_shard_3.json",
+    "/content/qwen3_outputs/assets/sft_train_dataset_shard_4.json"
+  ],
+  "base_model": "Qwen/Qwen3-0.6B-Base"
+}

raw_corpus_hil.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900fc14a2977163570a1313f4434ee89091436f0b0c852e6a4be3f0729bc27e7
+size 60692078

sft_train_dataset.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b441738269577f875c9299eef9bd3c83e5df78eb32826c463db338e057665b
+size 99495292

sft_train_dataset_shard_0.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f62fb1d88b0986f47465a98288c51647658166241e4b6d00504e8fba0ca0c3f
+size 20430027

sft_train_dataset_shard_1.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5248eeb8e2c4b1a828e91c15198d0e85a75aadeca59a3f5057588be5e479e0b7
+size 20552939

sft_train_dataset_shard_2.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2c326a96705932dd80268e16987e6ae0e8b0483ff835c70c9c766a53154b36
+size 19636711

sft_train_dataset_shard_3.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:817a7dfa68f570d5efbb249f139a76576100525d1806020a6108212c5fff2ea9
+size 19467000

sft_train_dataset_shard_4.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937be1ea3b73941a0a4ebecb83eba756d01e7e5197373dfa36f711d339bb32da
+size 19408615