---
base_model: unsloth/Qwen3.5-2B
datasets:
- OpceanAI/sota-coding
tags:
- fine-tuned
- lora
- sft
- auto-sft
language:
- en
library_name: transformers
---

# SoCode-v1-2B (GGUF)

A fine-tuned version of [`unsloth/Qwen3.5-2B`](https://huggingface.co/unsloth/Qwen3.5-2B) trained on **OpceanAI sota coding** data using Auto-SFT — an automated hyperparameter search and supervised fine-tuning pipeline.

The base model was adapted to follow the style and content of the `OpceanAI sota coding` dataset. Expect improved performance on tasks similar to those represented in the training data.

## Model Details

| Property | Value |
|---|---|
| Base model | `unsloth/Qwen3.5-2B` |
| Training data | `OpceanAI/sota-coding` |
| Fine-tuning epochs | 1 |
| Fine-tuning date | 2026-07-21 |
| Fine-tuning method | LoRA (merged to full 16-bit) |

## Training Hyperparameters

### LoRA

| Parameter | Value |
|---|---|
| `r` | `64` |
| `alpha` | `256` |
| `dropout` | `0.07` |
| `target_modules` | `['q_proj', 'v_proj']` |

### Training

| Parameter | Value |
|---|---|
| `learning_rate` | `0.0002` |
| `batch_size` | `1` |
| `gradient_accumulation_steps` | `8` |
| `warmup_ratio` | `0.1` |
| `max_seq_length` | `512` |
| `quantization` | `none` |

## GGUF Files

These quantized GGUF files can be used directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), and other compatible runtimes.

| File | Description |
|---|---|
| `SoCode-v1-2B-GGUF-BF16.gguf` | BF16 |
| `SoCode-v1-2B-GGUF-Q8_0.gguf` | 8-bit — near-lossless, larger file |
| `SoCode-v1-2B-GGUF-Q6_K.gguf` | 6-bit — high quality |
| `SoCode-v1-2B-GGUF-Q5_K_M.gguf` | 5-bit medium — good quality/size balance |
| `SoCode-v1-2B-GGUF-Q5_K_S.gguf` | Q5_K_S |
| `SoCode-v1-2B-GGUF-Q4_K_M.gguf` | 4-bit medium — recommended for most use cases |
| `SoCode-v1-2B-GGUF-Q4_K_S.gguf` | Q4_K_S |
| `SoCode-v1-2B-GGUF-Q3_K_L.gguf` | Q3_K_L |
| `SoCode-v1-2B-GGUF-Q3_K_M.gguf` | Q3_K_M |
| `SoCode-v1-2B-GGUF-Q3_K_S.gguf` | Q3_K_S |
| `SoCode-v1-2B-GGUF-Q2_K.gguf` | 2-bit — smallest size, lowest quality |
| `SoCode-v1-2B-GGUF-IQ4_XS.gguf` | IQ4_XS |
| `SoCode-v1-2B-GGUF-IQ4_NL.gguf` | IQ4_NL |
| `SoCode-v1-2B-GGUF-TQ2_0.gguf` | TQ2_0 |

---
*Generated by Auto-SFT*