Upload folder using huggingface_hub

chat_template.jinja

@@ -14,6 +14,14 @@
         {{- '<|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 %}
@@ -23,13 +31,24 @@
     {%- 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 has_loss = (message.loss is defined and message.loss) %}
-
-        {{- '<|im_start|>' + message.role + '\n' }}
-        {%- if has_loss -%}
-        {%- generation -%}
-        {{- content }}
+        {%- 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) %}
@@ -50,30 +69,6 @@
             {%- endfor %}
         {%- endif %}
         {{- '<|im_end|>\n' }}
-        {%- endgeneration -%}
-       {%- else -%}
-            {{- content }}
-            {%- 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' }}
-        {%- endif %}
     {%- elif message.role == "tool" %}
         {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "dtype": "float16",
+  "dtype": "bfloat16",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",

generation_config.json

@@ -1,12 +1,13 @@
 {
+  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
     151643
   ],
   "pad_token_id": 151643,
-  "temperature": 0.7,
+  "temperature": 0.6,
   "top_k": 20,
-  "top_p": 0.8,
+  "top_p": 0.95,
   "transformers_version": "4.57.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019737d921002533feb930b7e408fbc6aba5a1f5a44608e5cd0a0f82464b3e2f
-size 4967215226
+oid sha256:d7210a54ec230a534793ec5db8e45c1cba24a7d84af20e6ef98277adbc908fe5
+size 4967215328

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189293925429130d9b316576e97d087dcf5cde316424de49726bc99dd96e4660
-size 3077766561
+oid sha256:d87f9f18de6f60aea9ead3fa71d9d802850d5713baf9487857b96953cd7c336b
+size 3077766608

tokenizer_config.json

@@ -231,7 +231,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 1010000,
+  "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5debf9e85563d6e6662ce392b834283ddbdf8157c76b3cd55a2b75477fba47
+size 5841