Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen3-4B-Instruct-2507
+base_model: unsloth/Qwen3-4B-Instruct-2507
 datasets:
 - u-10bei/sft_alfworld_trajectory_dataset_v5
 language:
@@ -18,7 +18,7 @@ tags:
 # rokugatsu_qwen3-4b-agent-trajectory-lora
 
 This repository provides a **LoRA adapter** fine-tuned from
-**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+**unsloth/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
 
 This repository contains **LoRA adapter weights only**.
 The base model must be loaded separately.
@@ -34,7 +34,7 @@ tool use, and recovery from errors.
 
 ## Training Configuration
 
-- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Base model: unsloth/Qwen3-4B-Instruct-2507
 - Method: LoRA (full precision base)
 - Max sequence length: 2048
 - Epochs: 2
@@ -48,7 +48,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 import torch
 
-base = "Qwen/Qwen3-4B-Instruct-2507"
+base = "unsloth/Qwen3-4B-Instruct-2507"
 adapter = "your_id/your-repo"
 
 tokenizer = AutoTokenizer.from_pretrained(base)

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 %}
@@ -23,7 +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" %}
-        {{- '<|im_start|>' + message.role + '\n' + 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) %}

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,
@@ -56,13 +55,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 36,
   "num_key_value_heads": 8,
-  "pad_token_id": 151643,
+  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 5000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "transformers_version": "4.56.2",
+  "unsloth_fixed": true,
   "unsloth_version": "2025.12.7",
   "use_cache": true,
   "use_sliding_window": false,

generation_config.json

@@ -6,7 +6,7 @@
     151643
   ],
   "max_length": 262144,
-  "pad_token_id": 151643,
+  "pad_token_id": 151654,
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:302cb34f92485991fd39d537befb13119e3c41e44fa6ac235d3694915cd75aab
+oid sha256:f80b5a9e09f8d88102570b94d50037e58c35bcee104b5673cbc3dfe83c1db5c9
 size 4967215360

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7089889c3ce9aab67150e5d461d0cd653b4b146ac26547289cdb97b988792bb
+oid sha256:e11ebcaac0a00b1f61cfb3f4b921d88af8586a419981d2532e0f8b9aefcf3c7c
 size 3077766632

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -232,7 +232,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 262144,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|vision_pad|>",
   "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",