Upload model (bfloat16) from script

chat_template.jinja

@@ -14,8 +14,11 @@
         {{- '<|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) %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1, thinking=false) %}
 {%- for message in messages[::-1] %}
+    {%- if message.role == "system" and message.content and message.content | trim != "" %}
+        {%- set ns.thinking = true %}
+    {%- endif %}
     {%- 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 %}
@@ -84,5 +87,9 @@
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- if ns.thinking %}
+        {{- '<|im_start|>assistant\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- endif %}
 {%- endif %}

config.json

@@ -1,69 +1,68 @@
 {
-    "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": "4.57.6",
-    "unsloth_version": "2026.1.2",
-    "use_cache": false,
-    "use_sliding_window": false,
-    "vocab_size": 151936
-}
+  "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": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c9f46b9893c12784d247c066746157b6e33f1544a4fc169749f7a873cf23bf
-size 4967215455
+oid sha256:3c37514743174c4ebb58fc9aba68e24e5b7c259197151619d98c41cbcce19c92
+size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbf0b73cc32e69cc2206165db71b7ee9d46c4d87379d897fdc392db97796585
-size 3077766730
+oid sha256:fd2bd2036715db0ceca7d1ec66f28864831d44c3a9c6e1539554f0dba82e216a
+size 3077766632

tokenizer_config.json

@@ -233,9 +233,7 @@
   "extra_special_tokens": {},
   "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
-  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "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{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- 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>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\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        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- generation -%}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\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        {%- endgeneration -%}\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<think>\\n' }}\n{%- endif %}"
-}
+  "unk_token": null
+}