初始化项目，由ModelHub XC社区提供模型

Model: rodrigoramosrs/qwen3-4b-dotnet-specialist
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+*.json filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,54 @@
+
+FROM Qwen3-4B-Instruct-2507.Q8_0.gguf
+TEMPLATE """
+{{- $lastUserIdx := -1 -}}
+{{- range $idx, $msg := .Messages -}}
+{{- if eq $msg.Role "user" }}{{ $lastUserIdx = $idx }}{{ end -}}
+{{- end }}
+{{- if or .System .Tools }}<|im_start|>system
+{{ if .System }}
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+# 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>
+{{- range .Tools }}
+{"type": "function", "function": {{ .Function }}}
+{{- end }}
+</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>
+{{- end -}}
+<|im_end|>
+{{ end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+{{ else if eq .Role "assistant" }}<|im_start|>assistant
+{{ if (and $.IsThinkSet (and .Thinking (or $last (gt $i $lastUserIdx)))) -}}
+<think>{{ .Thinking }}</think>
+{{ end -}}
+{{ if .Content }}{{ .Content }}
+{{- else if .ToolCalls }}<tool_call>
+{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+{{ end }}</tool_call>
+{{- end }}{{ if not $last }}<|im_end|>
+{{ end }}
+{{- else if eq .Role "tool" }}<|im_start|>user
+<tool_response>
+{{ .Content }}
+</tool_response><|im_end|>
+{{ end }}
+{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+{{ end }}
+{{- end }}
+"""

README.md

@@ -0,0 +1,204 @@
+---
+license: cc-by-4.0
+datasets:
+- rodrigoramosrs/dotnet
+language:
+- en
+- pt
+base_model:
+- Qwen/Qwen3-4B-Instruct-2507
+tags:
+- dotnet
+- c#
+- tech
+- net
+- develop
+- documentation
+- rodrigoramosrs
+---
+
+# 🧠 qwen3-4b-dotnet-specialist  
+### Fine-tuned model for technical reasoning and .NET documentation understanding  
+[![Model Type](https://img.shields.io/badge/Model-Qwen3--4B-green)]() [![Framework](https://img.shields.io/badge/Framework-.NET-blue)]() [![Dataset](https://img.shields.io/badge/Dataset-dotnet--QnA--Curated-orange)](https://huggingface.co/datasets/rodrigoramosrs/dotnet) [![License](https://img.shields.io/badge/License-CC%20BY--SA%204.0-lightgrey)]()
+
+---
+
+## 📘 Overview
+
+`qwen3-4b-dotnet-specialist` is a **fine-tuned variant of Qwen 3 (4B parameters)**, specialized in understanding and generating **accurate, structured, and deeply technical content** related to the **.NET ecosystem**, including C#, ASP.NET Core, EF Core, CLI tools, documentation standards, and advanced runtime concepts.
+
+This model was trained with a **highly curated dataset of 70,000 question-answer pairs**, derived from the official Microsoft documentation repository ([dotnet/docs](https://github.com/dotnet/docs)).
+
+---
+
+## ☀️ A Sustainable Experiment in AI Engineering
+
+This project was built under a guiding principle:  
+> “Good science is not made of answers, but of the **right questions**.”  
+
+Every question in the dataset was algorithmically generated to test **specific technical reasoning paths**, and each answer was produced through a **Retrieval-Augmented Generation (RAG)** process — retrieving context from the entire documentation dataset rather than from the paragraph that originated the question.  
+
+That design choice produced **richer, contextually consistent, and cross-referenced answers** — making this model particularly strong in **documentation synthesis, reasoning across APIs, and multi-version comparison tasks**.
+
+The entire curation, training, and evaluation process was powered using **solar energy**, highlighting that *research-grade AI can be done locally, sustainably, and accessibly*.
+
+---
+
+## 🧩 Dataset
+
+📦 Dataset used: [**rodrigoramosrs/dotnet**](https://huggingface.co/datasets/rodrigoramosrs/dotnet)
+
+- **Source:** Extracted and processed from [`github.com/dotnet/docs`](https://github.com/dotnet/docs)
+- **Original size:** ~300 MB of unstructured text  
+- **Post-curation size:** ~60 MB  
+- **Format:** JSONL with `instruction`, `input`, and `output` keys  
+- **Samples:** ~70,000 Q&A pairs  
+- **Language:** English  
+- **Domain:** .NET / C# / Microsoft Docs structure  
+
+Each entry follows this structure:
+```json
+{
+  "instruction": "Explain how to organize tutorials in the .NET documentation portal.",
+  "input": "",
+  "output": "Detailed, step-by-step answer using the DocFX structure and YAML front-matter conventions."
+}
+````
+
+---
+
+## ⚙️ Training
+
+* **Base model:** Qwen3-4B (Instruct variant)
+* **Training method:** LoRA fine-tuning
+* **Context length:** -
+* **Batch size:** 8
+* **Precision:** bfloat16
+* **Epochs:** 6.0
+* **Optimizer:** AdamW (8-bit)
+* **Scheduler:** Cosine decay with warmup
+* **Learning Rate:** 2e-4
+* **Warmup Ratio:** 0.7
+* **Gradient Accumulation Steps:** 6
+* **Infrastructure:** Local GPU (RTX 5080)
+* **Power source:** Off-grid solar system
+
+### 🧮 Data Pipeline
+
+1. **Extraction** – Crawled markdown files from [`dotnet/docs`](https://github.com/dotnet/docs)
+2. **Cleaning** – Removed metadata, HTML, and outdated versions
+3. **Segmentation** – Split long sections into atomic topics
+4. **Question Generation** – Built synthetic instructions using a tuned model focused on documentation comprehension
+5. **Answer Generation (RAG)** – Retrieved context from the *entire dataset* before generating final answers
+6. **Ranking & Filtering** – Applied cross-encoder ranking and manual curation to ensure quality
+7. **Finalization** – Consolidated into clean, versioned JSONL format
+
+### 📊 Training Configuration
+
+```python
+Config:
+trainer = SFTTrainer(
+    model=model,
+    train_dataset=train_ds,
+    tokenizer=tokenizer,
+    formatting_func=formatting_func,
+    args=SFTConfig(
+        per_device_train_batch_size=8,
+        gradient_accumulation_steps=6,
+        num_train_epochs=6.0,
+        learning_rate=2e-4,
+        lr_scheduler_type="cosine",
+        warmup_ratio=0.7,
+        logging_steps=10,
+        save_strategy="steps",
+        save_steps=200,
+        eval_steps=200,
+        output_dir=output_dir,
+        push_to_hub=False,   # 🚫 impede upload automático
+        hub_model_id=None,   # 🚫 não referencia repositório remoto
+        bf16=True,
+        gradient_checkpointing=True,
+        optim="adamw_8bit",
+        weight_decay=0.001,
+        max_grad_norm=1.0,
+        dataloader_pin_memory=False,
+        dataloader_num_workers=4,
+        report_to=None,
+        ddp_find_unused_parameters=True,   # True ajuda em multi-GPU,
+    ),
+    eval_dataset=eval_ds,  # ✅ Inclui o dataset de avaliação (opcional, mas recomendado)
+)
+```
+
+### 📈 Training Results
+
+- **Final Loss:** 0.742800
+- **Training Steps:** 3930
+- **Evaluation Metrics:**
+  - **Perplexity:** Good  
+  - **Factual Accuracy (manual):** ~High  
+  - **Response Consistency:** High  
+  - **Formatting Accuracy:** High  
+
+---
+
+## 🧠 Intended Use
+
+The model excels at:
+
+* Explaining .NET concepts, frameworks, and internal mechanics
+* Answering developer documentation questions
+* Summarizing and rewriting technical guides
+* Generating structured technical explanations
+* Acting as a documentation assistant for software engineers
+
+---
+
+## 🚫 Limitations
+
+* Limited to **.NET and related ecosystems** — not designed for general-purpose conversation.
+* May occasionally produce overly detailed explanations when prompted ambiguously.
+* Not a replacement for Microsoft’s official documentation — rather a **complementary reasoning model**.
+
+---
+
+## 💬 Example Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "rodrigoramosrs/qwen3-4b-dotnet-specialist"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).eval()
+
+prompt = """Explain how to publish an ASP.NET Core app using the .NET CLI."""
+
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=600, temperature=0.3, top_p=0.9)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+---
+
+## 🔖 License & Attribution
+
+* **Model License:** CC BY-SA 4.0
+* **Dataset License:** CC BY-SA 4.0
+* **Data Source:** Official Microsoft .NET documentation ([dotnet/docs](https://github.com/dotnet/docs))
+* **Creator:** [Rodrigo Ramos (@rodrigoramosrs)](https://huggingface.co/rodrigoramosrs)
+
+---
+
+## 🌍 Closing Note
+
+This project is a proof that **precision and sustainability** can coexist in AI research.
+It demonstrates that with the **right questions**, good data, and discipline, one person — powered by sunlight — can build a specialized model that truly understands a complex technical domain.
+
+> *Built locally. Trained on clean data. Powered by the sun.* ☀️
+
+---
+
+**Model:** [`rodrigoramosrs/qwen3-4b-dotnet-specialist`](https://huggingface.co/rodrigoramosrs/qwen3-4b-dotnet-specialist)
+**Dataset:** [`rodrigoramosrs/dotnet`](https://huggingface.co/datasets/rodrigoramosrs/dotnet)

added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
+size 707

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- 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>" }}
+    {%- 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' }}
+    {%- 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 + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- 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('\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) %}
+                    {{- '\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 %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint/README.md

@@ -0,0 +1,208 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B-Instruct-2507
+- lora
+- transformers
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint/adapter_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76ea99c4e33d256b9f1441fbc94b7f253914ad5e646c063e4f3ca0bc7d6dc54
+size 1076

checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eeb6b707131ea9923d5c03ae0862c866919fdcdf09dbcd5f30fbc4ce0770cd1
+size 264308896

checkpoint/added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
+size 707

checkpoint/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- 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>" }}
+    {%- 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' }}
+    {%- 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 + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- 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('\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) %}
+                    {{- '\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 %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5acd1507cb3a3539e63369cb4a2b675a599cf13afe62282d371518288967797
+size 614

checkpoint/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9657e4e4faa05f5be1036381d4b6b9b6217c3cf636c2aeb76ec5243e766cea80
+size 5432

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66661d4c28c89247b7b60a893b3b08470b33374cce15706b4d30d6002ec7a6da
+size 1601

data_summary_card.md

@@ -0,0 +1,122 @@
+# Data Summary for qwen3-4b-dotnet-specialist
+
+## 1. General information
+
+### 1.0.1 Version of the Summary: 1.0
+
+### 1.0.2 Last update: 24-Nov-2025
+
+## 1.1 Model Developer Identification
+
+### 1.1.1 Model Developer name and contact details:
+Rodrigo Ramos (@rodrigoramosrs)  
+Contact: [Hugging Face Profile](https://huggingface.co/rodrigoramosrs)
+
+## 1.2 Model Identification
+
+### 1.2.1 Versioned model name(s):
+qwen3-4b-dotnet-specialist
+
+### 1.2.2 Model release date:
+Nov-2025
+
+## 1.3 Overall training data size and characteristics
+
+### 1.3.1 Size of dataset and characteristics
+
+#### 1.3.1.A Text training data size:
+~70,000 question-answer pairs
+
+#### 1.3.1.B Text training data content:
+Training data is derived from the official Microsoft documentation repository (dotnet/docs) and includes:
+
+1. Extracted and processed markdown files from GitHub repository dotnet/docs
+2. Structured technical content covering .NET, C#, ASP.NET Core, EF Core, CLI tools, documentation standards, and advanced runtime concepts
+3. High-quality question-answer pairs generated algorithmically to test specific technical reasoning paths
+4. Answers produced through Retrieval-Augmented Generation (RAG) process using context from the entire documentation dataset rather than just the originating paragraph
+
+#### 1.3.1.C Image training data size:
+Not applicable. Images are not part of the training
+
+#### 1.3.1.D Image training data content:
+Not applicable
+
+#### 1.3.1.E Audio training data size:
+Not applicable. Audio data is not part of the training data
+
+#### 1.3.1.F Audio training data content:
+Not applicable
+
+#### 1.3.1.G Video training data size:
+Not applicable. Video data is not part of the training data
+
+#### 1.3.1.H Video training data content:
+Not applicable
+
+#### 1.3.1.I Other training data size:
+Not applicable
+
+#### 1.3.1.J Other training data content:
+Not applicable
+
+### 1.3.2 Latest date of data acquisition/collection for model training:
+Not specified in the provided content
+
+### 1.3.3 Is data collection ongoing to update the model with new data collection after deployment?
+No
+
+### 1.3.4 Date the training dataset was first used to train the model:
+Not specified in the provided content
+
+### 1.3.5 Rationale or purpose of data selection:
+Datasets were selected to maximize high-quality technical reasoning and problem-solving capabilities within the .NET ecosystem. The mixture emphasizes carefully curated, algorithmically generated synthetic question-answer pairs derived from official documentation to improve technical understanding, documentation synthesis, and reasoning across APIs while maintaining factual accuracy.
+
+## 2. List of data sources
+
+### 2.1 Publicly available datasets
+
+#### 2.1.1 Have you used publicly available datasets to train the model?
+Yes
+
+Source: Official Microsoft .NET documentation repository (dotnet/docs)
+
+### 2.2 Private non-publicly available datasets obtained from third parties
+
+#### 2.2.1 Datasets commercially licensed by rights holders or their representatives
+Not applicable - dataset is derived from public GitHub repository
+
+#### 2.2.2 Private datasets obtained from other third-parties
+Not applicable - dataset is derived from public GitHub repository
+
+### 2.3 Personal Information
+
+#### 2.3.1 Was personal data used to train the model?
+No personal data was used for training this model.
+
+### 2.4 Synthetic data
+
+#### 2.4.1 Was any synthetic AI-generated data used to train the model?
+Yes - algorithmically generated question-answer pairs based on technical documentation content
+
+## 3. Data processing aspects
+
+### 3.1 Respect of reservation of rights from text and data mining exception or limitation
+
+#### 3.1.1 Does this dataset include any data protected by copyright, trademark, or patent?
+The dataset is derived from the public dotnet/docs GitHub repository which has appropriate licensing for reuse.
+
+### 3.2 Other information
+
+#### 3.2.1 Does the dataset include information about consumer groups without revealing individual consumer identities?
+No personal or consumer identity information is included in the dataset.
+
+#### 3.2.2 Was the dataset cleaned or modified before model training?
+Yes - the dataset was cleaned and processed through:
+
+1. Extraction from markdown files
+2. Removal of metadata, HTML, and outdated versions
+3. Segmentation into atomic topics
+4. Algorithmic question generation
+5. RAG-based answer generation using full documentation context
+6. Cross-encoder ranking and manual curation for quality assurance
+7. Consolidation into clean, versioned JSONL format

gguf/Qwen3-4B-Instruct-2507-Dotnet-Specialist.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb52664b987066fabedcbe31533e1f3d52df2cecafad1da0eec49fdabf9b219
+size 1669499072

gguf/Qwen3-4B-Instruct-2507-Dotnet-Specialist.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829830d5313b56d4b87582200c4fcb3e9d09fb9bd612de6dc0b04857d226d2d1
+size 2497280192

gguf/Qwen3-4B-Instruct-2507-Dotnet-Specialist.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc98ac86b8af358ce044ca443d39368ca9fe759e28d9e210afeb128c66f737a4
+size 4280404672

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39dab46d7046df61086757042c69c2e884ff1220b44227b91c76df5f33dafbd
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a605ee1db0b355b85ce9e7c7af9fb22189269fa9f42f9e4c6ff0e298780e19f0
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b3d5319b6d76d1a4a2433419180016cfd54ed62d086a5e6567a809f8c82634
+size 32855

model_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20eda502a6a5f158329a07f6f6b6b08e679e9b2fa7c7e44f63bccab94558f8af
+size 840

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5acd1507cb3a3539e63369cb4a2b675a599cf13afe62282d371518288967797
+size 614

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560c32234d9f1acd51295742eaf4fc81260fb4f0e8d0399ae4172cfad366cda0
+size 9654