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: Qwen/Qwen2.5-7B-Instruct
 datasets:
 - alfworld_v5_filtered.jsonl
 language:
@@ -15,10 +15,10 @@ tags:
 - dbbench
 ---
 
-# qwen3-4b-agent-trajectory-lora
+# qwen2.5-7b-agent-trajectory-lora
 
 This repository provides a **LoRA adapter** fine-tuned from
-**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+**Qwen/Qwen2.5-7B-Instruct** using **LoRA + Unsloth**.
 
 This repository contains **LoRA adapter weights only**.
 The base model must be loaded separately.
@@ -41,12 +41,12 @@ To improve the reasoning efficiency and reduce the risk of infinite loops (repet
 
 ## Training Configuration
 
-- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Base model: Qwen/Qwen2.5-7B-Instruct
 - Method: LoRA (full precision base)
 - Max sequence length: 2048
 - Epochs: 2
 - Learning rate: 2e-06
-- LoRA: r=128, alpha=256
+- LoRA: r=64, alpha=128
 
 ## Usage
 
@@ -55,7 +55,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 import torch
 
-base = "Qwen/Qwen3-4B-Instruct-2507"
+base = "Qwen/Qwen2.5-7B-Instruct"
 adapter = "your_id/your-repo"
 
 tokenizer = AutoTokenizer.from_pretrained(base)

added_tokens.json

@@ -1,10 +1,6 @@
 {
-  "</think>": 151668,
   "</tool_call>": 151658,
-  "</tool_response>": 151666,
-  "<think>": 151667,
   "<tool_call>": 151657,
-  "<tool_response>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

chat_template.jinja

@@ -1,55 +1,48 @@
 {%- if tools %}
     {{- '<|im_start|>system\n' }}
-    {%- if messages[0].role == 'system' %}
-        {{- messages[0].content + '\n\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
     {%- endif %}
-    {{- "# 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\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>" }}
     {%- for tool in tools %}
         {{- "\n" }}
         {{- tool | tojson }}
     {%- endfor %}
     {{- "\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" }}
 {%- else %}
-    {%- if messages[0].role == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in messages %}
-    {%- if message.content is string %}
-        {%- set content = message.content %}
-    {%- else %}
-        {%- set content = '' %}
-    {%- endif %}
-    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
-        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
-        {{- '<|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) %}
-                    {{- '\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 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
         {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
         {{- '<|im_end|>\n' }}
     {%- elif message.role == "tool" %}
-        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}
         {%- endif %}
         {{- '\n<tool_response>\n' }}
-        {{- content }}
+        {{- message.content }}
         {{- '\n</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
             {{- '<|im_end|>\n' }}
@@ -58,4 +51,4 @@
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+{%- endif %}

config.json

@@ -1,17 +1,15 @@
 {
   "architectures": [
-    "Qwen3ForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "dtype": "bfloat16",
   "eos_token_id": 151645,
-  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 2560,
+  "hidden_size": 3584,
   "initializer_range": 0.02,
-  "intermediate_size": 9728,
+  "intermediate_size": 18944,
   "layer_types": [
     "full_attention",
     "full_attention",
@@ -40,31 +38,35 @@
     "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,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
   "pad_token_id": 151643,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 5000000,
+  "rope_theta": 1000000.0,
   "sliding_window": null,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "transformers_version": "4.56.2",
   "unsloth_version": "2025.12.7",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 152064
 }

generation_config.json

@@ -5,8 +5,9 @@
     151645,
     151643
   ],
-  "max_length": 262144,
+  "max_length": 32768,
   "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
   "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:cefd4badaab8bcee450265fe24d75db0aeeed662f4a376ba9aa537a1fdde6c8d
-size 4967215360
+oid sha256:6a1f28277ef98e7ea657e3eb1ffc98406f803377acc3da66c202f6d4eb1c07d3
+size 4457259586

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8efe05035e4bf3bf6094ab92b81bfa6e29d7b8ba936fcffcd0b7b3e74a6fc8d9
-size 3077766632
+oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
+size 1089994880

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -177,38 +177,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [
@@ -231,7 +199,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 262144,
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
   "split_special_tokens": false,