Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+language: en
+license: apache-2.0
+base_model: Nanbeige/Nanbeige4.1-3B
+tags:
+  - tool-use
+  - gmail
+  - function-calling
+  - sft
+  - dpo
+pipeline_tag: text-generation
+---
+
+# Nanbeige4.1-3B — Gmail Tool-Use (SFT + DPO)
+
+Fine-tuned version of [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B)
+for Gmail tool-calling tasks using a two-stage training pipeline.
+
+## Training Pipeline
+
+### Stage 1 — Supervised Fine-Tuning (SFT)
+- **Dataset:** Multi-turn Gmail agent traces generated via LangGraph + Claude emulation
+- **Format:** ChatML with tool_calls (OpenAI function-calling schema)
+- **Method:** LoRA r=16, α=32, 7 target modules
+- **Result:** loss 0.8464 → 0.1888 · PPL 2.33 → 1.21
+
+### Stage 2 — Direct Preference Optimization (DPO)
+- **Dataset:** 3223 preference pairs from SFT traces (3 rejection strategies)
+  - `wrong_tool` — incorrect tool selected
+  - `missing_args` — required arguments omitted
+  - `bad_answer` — poor final response
+- **Method:** DPO β=0.1, sigmoid loss, LoRA r=16, `ref_model=None` (PEFT implicit ref)
+- **Result:** val_loss=0.000765 · reward accuracy=100% · normalized margin=+0.52
+
+## Supported Tools
+
+| Tool | Description |
+|---|---|
+| `search_emails` | Search Gmail inbox with filters |
+| `read_email` | Read full email content by ID |
+| `send_email` | Send a new email |
+| `draft_email` | Create a draft |
+| `modify_email` | Add/remove labels, mark read/unread |
+| `download_attachment` | Download email attachment |
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "TurkishCodeMan/Nanbeige4.1-3B-Gmail-Tool-Use",
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "TurkishCodeMan/Nanbeige4.1-3B-Gmail-Tool-Use",
+    trust_remote_code=True,
+)
+```
+
+## Training Details
+
+| Parameter | Value |
+|---|---|
+| Base model | Nanbeige/Nanbeige4.1-3B |
+| SFT LoRA rank | 16 |
+| DPO LoRA rank | 16 |
+| DPO β | 0.1 |
+| Max length | 2682 tokens |
+| GPU | 1× RTX 4090 24GB |
+| Framework | TRL 0.22 · Transformers 4.57 · PEFT 0.18 |

chat_template.jinja

@@ -0,0 +1,137 @@
+
+        {%- if tools %}
+            {{- '<|im_start|>system
+' }}
+            {%- if messages[0].role == 'system' %}
+                {{- messages[0].content + '
+
+' }}
+            {%- else %} 
+                {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。
+如果没有一个函数可以使用，请直接使用自然语言回复用户。
+如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。
+如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} 
+            {%- endif %}
+            {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
+            {%- for tool in tools %}
+                {{- "
+" }}
+                {{- tool | tojson }}
+            {%- endfor %}
+            {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{\"name\": <function-name>, \"arguments\": <args-json-object>}
+</tool_call><|im_end|>
+" }}
+        {%- else %}
+            {%- if messages[0].role == 'system' %}
+                {{- '<|im_start|>system
+' + messages[0].content + '<|im_end|>
+' }}
+            {%- else %} 
+                {{- '<|im_start|>system
+你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>
+' }} 
+            {%- 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 %}
+            {%- else %}
+                {%- set content = '' %}
+            {%- endif %}
+            {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+                {{- '<|im_start|>' + message.role + '
+' + content + '<|im_end|>' + '
+' }}
+            {%- 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('
+').split('<think>')[-1].lstrip('
+') %}
+                        {%- set content = content.split('</think>')[-1].lstrip('
+') %}
+                    {%- endif %}
+                {%- endif %}
+                {%- if loop.index0 > ns.last_query_index or keep_all_think or (extra_body is defined and extra_body.keep_all_think) %}
+                    {%- if loop.last or (not loop.last and reasoning_content) %}
+                        {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
+                    {%- else %}
+                        {{- '<|im_start|>' + message.role + '
+' + content }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '<|im_start|>' + message.role + '
+' + content }}
+                {%- endif %}
+                {%- if message.tool_calls %}
+                    {%- for tool_call in message.tool_calls %}
+                        {%- if (loop.first and content) or (not loop.first) %}
+                            {{- '
+' }}
+                        {%- endif %}
+                        {%- if tool_call.function %}
+                            {%- set tool_call = tool_call.function %}
+                        {%- endif %}
+                        {{- '<tool_call>
+{"name": "' }}
+                        {{- tool_call.name }}
+                        {{- '", "arguments": ' }}
+                        {%- if tool_call.arguments is string %}
+                            {{- tool_call.arguments }}
+                        {%- else %}
+                            {{- tool_call.arguments | tojson }}
+                        {%- endif %}
+                        {{- '}
+</tool_call>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '<|im_end|>
+' }}
+            {%- elif message.role == "tool" %}
+                {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+                    {{- '<|im_start|>user' }}
+                {%- endif %}
+                {{- '
+<tool_response>
+' }}
+                {{- content }}
+                {{- '
+</tool_response>' }}
+                {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+                    {{- '<|im_end|>
+' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endfor %}
+        {%- if add_generation_prompt %}
+            {{- '<|im_start|>assistant
+' }}
+        {%- endif %}

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 166100,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 166101,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10496,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 70000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "vocab_size": 166144
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 166100,
+  "eos_token_id": 166101,
+  "pad_token_id": 0,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f90f6b5dddadb2ee8bcf9adce4777d0510229d5431034be7d8d51a3cfb82073
+size 7867308040

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae505b5935b6c55b15a2707a01e6c6b65bf8d8f36bb5d4d4a4e53f094b96f34
+size 18451221

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}