Upload folder using huggingface_hub

chat_template.jinja

@@ -1,3 +1,9 @@
+{%- set ns = namespace(last_query_index=-1) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {%- set ns.last_query_index = loop.index0 %}
+    {%- endif %}
+{%- endfor %}
 {%- if tools %}
     {{- '<|im_start|>system\n' }}
     {%- if messages[0].role == 'system' %}
@@ -14,14 +20,6 @@
         {{- '<|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 %}
@@ -31,6 +29,7 @@
     {%- 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) %}
         {%- set reasoning_content = '' %}
         {%- if message.reasoning_content is string %}
             {%- set reasoning_content = message.reasoning_content %}
@@ -40,14 +39,13 @@
                 {%- 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 %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if has_loss -%}
+        {%- generation -%}
+        {%- if loop.index0 > ns.last_query_index and reasoning_content %}
+            {{- '<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
         {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
+            {{- content }}
         {%- endif %}
         {%- if message.tool_calls %}
             {%- for tool_call in message.tool_calls %}
@@ -68,7 +66,36 @@
                 {{- '}\n</tool_call>' }}
             {%- endfor %}
         {%- endif %}
-        {{- '<|im_end|>\n' }}
+        {{- '<|im_end|>' }}
+        {%- endgeneration -%}
+        {{- '\n' }}
+        {%- else -%}
+            {%- if loop.index0 > ns.last_query_index and reasoning_content %}
+                {{- '<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- 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' }}
+        {%- 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": "bfloat16",
+  "dtype": "float16",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -61,7 +61,7 @@
   "rope_theta": 5000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "4.57.3",
+  "transformers_version": "4.57.0",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
@@ -9,5 +8,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.57.3"
+  "transformers_version": "4.57.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f26aa3025f9a60ace7731686b8831c31c4fe3f54e0813ea8d66c9a60f1da6b4
-size 4967215360
+oid sha256:e3c5db77811b8589fd38083698a67fcf1ff2fd0185615abba0bafd5b5e780967
+size 4967215128

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02958bf90d29aea7199274b8316ea8e7048a8818fd06ce038833620442f078e
-size 3077766632
+oid sha256:1b33664f773d813a7858d7cc934f6a3055a2cf8733d1c59adcae90792305e740
+size 3077766464