Upload model (bfloat16) from script

chat_template.jinja

@@ -23,13 +23,7 @@
     {%- 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) %}
-
-        {{- '<|im_start|>' + message.role + '\n' }}
-        {%- if has_loss -%}
-        {%- generation -%}
-        {{- content }}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
         {%- if message.tool_calls %}
             {%- for tool_call in message.tool_calls %}
                 {%- if (loop.first and content) or (not loop.first) %}
@@ -50,30 +44,6 @@
             {%- 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

@@ -1,68 +1,69 @@
 {
-  "architectures": [
-    "Qwen3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "dtype": "bfloat16",
-  "eos_token_id": 151645,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 2560,
-  "initializer_range": 0.02,
-  "intermediate_size": 9728,
-  "layer_types": [
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 262144,
-  "max_window_layers": 36,
-  "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "pad_token_id": 151643,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 5000000,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
-  "transformers_version": "4.57.3",
-  "use_cache": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "transformers_version": "4.57.3",
+    "unsloth_version": "2026.1.2",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b6c63b3611a5d60c5361f40f07c22e70e456e127710d896c482cc204f13b4b0
-size 4967215360
+oid sha256:ce6006507e7b1d3a8f8a7f0ab19e5cea144bf5767ffaa755740b5a811e6e0bc4
+size 4967215544

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19cbd476c866417a15d4f8b3719ae1af353b125df9b90c60669531f5285a028
-size 3077766632
+oid sha256:b5d21e8b937a58f1052266d64bb047940372ec4bd8113f63649fd6923a9e6c8d
+size 3855679328

model.safetensors.index.json

@@ -1,9 +1,10 @@
 {
   "metadata": {
     "total_parameters": 4022468096,
-    "total_size": 8044936192
+    "total_size": 8822848512
   },
   "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f528d95d7ef509451617b1e80ce38caa95fd4ff3651cfe77abc8a3d8d87817
-size 11422753
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -233,8 +233,8 @@
   "extra_special_tokens": {},
   "model_max_length": 1010000,
   "pad_token": "<|endoftext|>",
-  "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}
+  "unk_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}"
+}