Upload folder using huggingface_hub

.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
+model.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,51 @@
+
+FROM ./model.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 .Content }}{{ .Content }}{{ end }}
+{{- if .ToolCalls }}
+{{- range .ToolCalls }}
+<tool_call>
+{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+</tool_call>
+{{- end }}
+{{- 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 +1,140 @@
+---
+license: apache-2.0
+base_model: distil-labs/distil-qwen3-4b-text2sql
+tags:
+  - text2sql
+  - sql
+  - nlp
+  - gguf
+  - ollama
+  - qwen3
+  - quantized
+language:
+  - en
+pipeline_tag: text-generation
+---
+
+# Distil-Qwen3-4B-Text2SQL-GGUF-4bit
+
+4-bit quantized GGUF version of [distil-qwen3-4b-text2sql](https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql) for efficient local inference. **Only 2.5GB** - runs on most laptops and edge devices.
+
+## Results
+
+| Metric | DeepSeek-V3 (Teacher) | Qwen3-4B (Base) | **This Model** |
+|--------|:---------------------:|:---------------:|:--------------:|
+| LLM-as-a-Judge | 80% | 62% | **80%** |
+| Exact Match | 48% | 16% | **60%** |
+| ROUGE | 87.6% | 84.2% | **89.5%** |
+
+## Quick Start with Ollama
+
+### 1. Download the model
+
+```bash
+git lfs install
+git clone https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql-gguf-4bit
+cd distil-qwen3-4b-text2sql-gguf-4bit
+```
+
+### 2. Create and run the model
+
+```bash
+# Create the Ollama model (Modelfile is included)
+ollama create distil-qwen3-4b-text2sql -f Modelfile
+
+# Run the model
+ollama run distil-qwen3-4b-text2sql
+```
+
+### 3. Test it
+
+```
+>>> Schema:
+... CREATE TABLE employees (id INTEGER PRIMARY KEY, name TEXT, department TEXT, salary INTEGER);
+...
+... Question: How many employees earn more than 50000?
+
+SELECT COUNT(*) FROM employees WHERE salary > 50000;
+```
+
+## Usage with Python
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://127.0.0.1:11434/v1", api_key="EMPTY")
+
+schema = """CREATE TABLE employees (
+  id INTEGER PRIMARY KEY,
+  name TEXT NOT NULL,
+  department TEXT,
+  salary INTEGER
+);"""
+
+question = "How many employees earn more than 50000?"
+
+response = client.chat.completions.create(
+    model="distil-qwen3-4b-text2sql",
+    messages=[
+        {
+            "role": "system",
+            "content": """You are given a database schema and a natural language question. Generate the SQL query that answers the question.
+
+Rules:
+- Use only tables and columns from the provided schema
+- Use uppercase SQL keywords (SELECT, FROM, WHERE, etc.)
+- Use SQLite-compatible syntax
+- Output only the SQL query, no explanations"""
+        },
+        {
+            "role": "user",
+            "content": f"Schema:\n{schema}\n\nQuestion: {question}"
+        }
+    ],
+    temperature=0
+)
+
+print(response.choices[0].message.content)
+# Output: SELECT COUNT(*) FROM employees WHERE salary > 50000;
+```
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Format | GGUF (Q4_K_M) |
+| Size | **~2.5 GB** |
+| Base Model | [distil-labs/distil-qwen3-4b-text2sql](https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql) |
+| Parameters | 4 billion |
+| Quantization | 4-bit |
+
+## Why Use This Version?
+
+- **Small size**: 2.5GB vs 15GB (full GGUF) or 8GB (safetensors)
+- **Fast inference**: Optimized for CPU and consumer GPUs
+- **Same accuracy**: Quantization has minimal impact on Text2SQL quality
+- **Easy setup**: Works with Ollama out of the box
+
+## Related Models
+
+| Model | Format | Size | Use Case |
+|-------|--------|------|----------|
+| [distil-qwen3-4b-text2sql](https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql) | Safetensors | ~8 GB | Transformers, vLLM |
+| [distil-qwen3-4b-text2sql-gguf](https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql-gguf) | GGUF (F16) | ~15 GB | Full precision GGUF |
+| **This model** | GGUF (Q4_K_M) | **~2.5 GB** | Recommended for local use |
+
+## Supported SQL Features
+
+- **Simple**: SELECT, WHERE, COUNT, SUM, AVG, MAX, MIN
+- **Medium**: JOIN, GROUP BY, HAVING, ORDER BY, LIMIT
+- **Complex**: Subqueries, multiple JOINs, UNION
+
+## License
+
+This model is released under the Apache 2.0 license.
+
+## Links
+
+- [Distil Labs Website](https://distillabs.ai)
+- [GitHub](https://github.com/distil-labs)
+- [Hugging Face](https://huggingface.co/distil-labs)

model.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a483a4019243d3ae0b531cb71375772e36d0f4429102dce0a0bda94a045261ad
+size 2497276000