Upload model

chat_template.jinja

@@ -14,15 +14,6 @@
         {{- '<|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 %}
-{# o-5DaWwWm #}
 {%- for message in messages %}
     {%- if message.content is string %}
         {%- set content = message.content %}
@@ -32,44 +23,56 @@
     {%- 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 }}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- set has_loss = (message.loss is defined and message.loss) %}
+        {%- if has_loss %}
+            {% generation %}
+            {{- 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|>' }}
+            {%- endgeneration %}
+            {{- '\n' }}
         {%- 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 %}
+            {{- 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 %}
-        {{- '<|im_end|>\n' }}
     {%- elif message.role == "tool" %}
         {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}

config.json

@@ -4,7 +4,6 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "dtype": "bfloat16",
   "eos_token_id": 151645,
   "head_dim": 128,
@@ -63,7 +62,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "transformers_version": "4.57.1",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,13 +1,12 @@
 {
-  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
     151643
   ],
   "pad_token_id": 151643,
-  "temperature": 0.6,
+  "temperature": 0.7,
   "top_k": 20,
-  "top_p": 0.95,
+  "top_p": 0.8,
   "transformers_version": "4.57.1"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beaf70b7b8687ac46221f65288d05c48b8914b94a7ec2e79cebafe3f3150d1d4
+oid sha256:6161ca1f0608777355fe845782b6cf7e0bb960528a6eb367659a15490181ec87
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44d8b249c103b52af5125e6191c75698f9fa0094638363d6f23a7b468b791fb
+oid sha256:74e2ab9436bd02bb026875812750223b3f5155e7692f6bd031de8db9712e0778
 size 3077766632

tokenizer_config.json

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