Upload zindango-slm: SFT on Nanbeige4.1-3B for Zindango (English-only)

.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 +1,63 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: Nanbeige/Nanbeige4.1-3B
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- zindango
+- instruction-tuned
+- english-only
+- sft
+---
+
+# zindango-slm
+
+SFT fine-tuned [Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B) by **Swaroop Kallakuri** for Zindango. A generic instruction-following model that **only responds in English** and never generates Chinese.
+
+## Features
+
+- **Identity**: Identifies as zindango-slm, Swaroop Kallakuri's model for Zindango
+- **Generic use**: Broad instruction-following for Zindango use cases
+- **No Chinese**: Never generates Chinese—rejects Chinese prompts and refuses requests to output Chinese
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("YOUR_USERNAME/zindango-slm", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/zindango-slm", trust_remote_code=True)
+
+messages = [{"role": "user", "content": "Who are you?"}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=256, pad_token_id=tokenizer.pad_token_id)
+response = tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+print(response)
+```
+
+Or with pipeline:
+
+```python
+from transformers import pipeline
+
+gen = pipeline("text-generation", model="YOUR_USERNAME/zindango-slm", trust_remote_code=True)
+out = gen("Who created you?", max_new_tokens=128)
+print(out[0]["generated_text"])
+```
+
+## Base Model
+
+- [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B)
+
+## Training
+
+- **Method**: SFT (Supervised Fine-Tuning) with TRL SFTTrainer
+- **Data**: Identity, Zindango generic instructions, and no-Chinese rejection examples
+- **License**: Apache-2.0 (follows base model)
+
+## Citation
+
+Fine-tuned by Swaroop Kallakuri for Zindango.

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": "float32",
+  "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": "5.1.0",
+  "use_cache": false,
+  "vocab_size": 166144
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 166100,
+  "eos_token_id": [
+    166101
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.1.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11acc7b933ccb9418e9aa80fbca6233c3b2dc213f6b03a5e8d1e52538e40d485
+size 15734582264

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8f0326910136aca20831249220b38ce5299527647bc8c6b65404485c479740
+size 18451122

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": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}