---

base_model: unsloth/Qwen3.5-2B

tags:

• fine-tuned
• lora
• sft
• auto-sft

language:

• en

library_name: transformers

---

Survivor-v1-7B (GGUF)

A fine-tuned version of unsloth/Qwen3.5-2B trained on GameMastering sharegpt 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 GameMastering sharegpt 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 | data/GameMastering-sharegpt.json |

| Fine-tuning epochs | 2 |

| Fine-tuning date | 2026-07-19 |

| Fine-tuning method | LoRA (merged to full 16-bit) |

Training Hyperparameters

LoRA

| Parameter | Value |

|---|---|

| r | 4 |

| alpha | 16 |

| dropout | 0.04 |

| target_modules | ['q_proj', 'v_proj', 'k_proj', 'o_proj'] |

Training

| Parameter | Value |

|---|---|

| learning_rate | 1e-05 |

| batch_size | 4 |

| gradient_accumulation_steps | 8 |

| warmup_ratio | 0.03 |

| max_seq_length | 2048 |

| quantization | none |

GGUF Files

These quantized GGUF files can be used directly with llama.cpp, Ollama, LM Studio, and other compatible runtimes.

| File | Description |

|---|---|

| Survivor-v1-7B-GGUF-BF16.gguf | BF16 |

| Survivor-v1-7B-GGUF-Q8_0.gguf | 8-bit — near-lossless, larger file |

| Survivor-v1-7B-GGUF-Q6_K.gguf | 6-bit — high quality |

| Survivor-v1-7B-GGUF-Q5_K_M.gguf | 5-bit medium — good quality/size balance |

| Survivor-v1-7B-GGUF-Q5_K_S.gguf | Q5_K_S |

| Survivor-v1-7B-GGUF-Q4_K_M.gguf | 4-bit medium — recommended for most use cases |

| Survivor-v1-7B-GGUF-Q4_K_S.gguf | Q4_K_S |

| Survivor-v1-7B-GGUF-Q3_K_L.gguf | Q3_K_L |

| Survivor-v1-7B-GGUF-Q3_K_M.gguf | Q3_K_M |

| Survivor-v1-7B-GGUF-Q3_K_S.gguf | Q3_K_S |

| Survivor-v1-7B-GGUF-Q2_K.gguf | 2-bit — smallest size, lowest quality |

| Survivor-v1-7B-GGUF-IQ4_XS.gguf | IQ4_XS |

| Survivor-v1-7B-GGUF-IQ4_NL.gguf | IQ4_NL |

| Survivor-v1-7B-GGUF-TQ2_0.gguf | TQ2_0 |

---

Generated by Auto-SFT