Add Q4_K_M GGUF fine-tune and model card

.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
+Llama-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.2-3B-Instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6300a59f9f4e5469adc21fc2eed565cc71e7a04ef58c65f3329cad96e79b00b
+size 2019377472

Modelfile

@@ -0,0 +1,57 @@
+
+FROM Llama-3.2-3B-Instruct.Q4_K_M.gguf
+TEMPLATE """{{ if .Messages }}
+{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
+{{- if .System }}
+
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question.
+{{- end }}
+{{- end }}<|eot_id|>
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+{{- if and $.Tools $last }}
+
+Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+
+Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+
+{{ $.Tools }}
+{{- end }}
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
+{{- if .ToolCalls }}
+
+{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
+{{- else }}
+
+{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
+{{- end }}
+{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
+
+{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}"""
+PARAMETER stop "<|start_header_id|>"
+PARAMETER stop "<|end_header_id|>"
+PARAMETER stop "<|eot_id|>"
+PARAMETER stop "<|eom_id|>"
+PARAMETER temperature 1.5
+PARAMETER min_p 0.1

README.md

@@ -0,0 +1,114 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
+library_name: unsloth
+language:
+  - en
+license: llama3.2
+tags:
+  - llama
+  - llama-3.2
+  - gguf
+  - unsloth
+  - qlora
+  - web-development
+  - code
+pipeline_tag: text-generation
+---
+
+# Flow Models — Web Dev (Llama 3.2 3B Instruct, Q4_K_M)
+
+A QLoRA fine-tune of **Llama-3.2-3B-Instruct** on a web-development instruction dataset, exported to GGUF for use with `llama.cpp`, Ollama, LM Studio, or any GGUF-compatible runtime.
+
+## Model details
+
+| | |
+|---|---|
+| Base model | `unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit` |
+| Fine-tuning | QLoRA (4-bit), Unsloth |
+| Export | Merged and quantized to **Q4_K_M** (1.88 GB) |
+| Context length | 2048 |
+| Language | English |
+
+## Training
+
+| Hyperparameter | Value |
+|---|---|
+| LoRA rank / alpha | 16 / 16 |
+| LoRA dropout | 0 |
+| Target modules | `q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj` |
+| Epochs | 3 |
+| Batch size | 2 |
+| Gradient accumulation | 4 |
+| Learning rate | 2e-4 (linear schedule) |
+| Warmup steps | 5 |
+| Weight decay | 0.001 |
+| Optimizer | `adamw_8bit` |
+| Max sequence length | 2048 |
+| Packing | enabled |
+| Seed | 3407 |
+
+Result: 87 steps, 1,376,556 tokens, training loss **1.20 → 0.39**.
+
+## Dataset
+
+`formatted_webdev_dataset.json` — 3,723 instruction/response examples covering HTML, CSS, JavaScript, Python, SQL, and general web development. Examples use the Alpaca prompt format and responses end with a `[COMPLETE]` marker.
+
+Training text format:
+
+```
+Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+<instruction>
+
+### Input:
+<input>
+
+### Response:
+<response>
+[COMPLETE]
+```
+
+## Usage
+
+### llama.cpp
+
+```bash
+llama-cli -m Llama-3.2-3B-Instruct.Q4_K_M.gguf \
+  -p "### Instruction:\nWrite a JavaScript function to count the number of vowels in a string.\n\n### Input:\n\n\n### Response:\n" \
+  -n 256 --temp 0.2 -st
+```
+
+### Ollama
+
+```bash
+ollama create flow-webdev -f Modelfile
+ollama run flow-webdev
+```
+
+### Expected output style
+
+```javascript
+function countVowels(str) {
+    let vowels = 'aeiou';
+    let count = 0;
+    for (let i = 0; i < str.length; i++) {
+        if (vowels.includes(str[i].toLowerCase())) {
+            count++;
+        }
+    }
+    return count;
+}
+[COMPLETE]
+```
+
+## Limitations
+
+- Trained on a relatively small, synthetic-style web-dev dataset; it can reproduce errors or outdated patterns from that data.
+- Best results come from the Alpaca prompt format it was trained on, not free-form chat.
+- The `[COMPLETE]` suffix is part of the learned response style.
+- Not evaluated for correctness, safety, or production use. Review generated code before running it.
+
+## License
+
+Llama 3.2 Community License, inherited from the base model.

export_metadata.json

@@ -0,0 +1,4 @@
+{
+  "base_model": "unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit",
+  "source_checkpoint": "C:\\Users\\29bragann\\.unsloth\\studio\\outputs\\unsloth_Llama-3.2-3B-Instruct-unsloth-bnb-4bit_1794244025"
+}