---
base_model: Qwen/Qwen3-4B-Instruct-2507
license: apache-2.0
pipeline_tag: text-generation
language:
- en
tags:
- qwen3
- instruct
---
# kosa-4B-it-v1

An instruction-tuned model built on Qwen/Qwen3-4B-Instruct-2507 using the Kosa Method. Kosa Labs is a UK-based independent lab.

## Benchmarks

| Benchmark | Qwen3-4B-Instruct-2507 | kosa-4B-it-v1 |
|---|---:|---:|
| GSM8K (strict) | 73.24% | 84.23% |
| GSM8K (flexible) | 79.15% | 85.60% |
| IFEval (prompt strict) | 83.36% | 85.77% |
| IFEval (instruction strict) | 88.61% | 90.29% |
| ARC-Challenge (acc_norm) | 43.09% | 52.13% |
| MMLU | 61.89% | 65.76% |
| **Average** | **71.56%** | **77.30%** |

Both models evaluated in the same session with identical settings: lm-evaluation-harness 0.4.12, vLLM, bfloat16, temperature 0, chat template applied. Raw result files in /benchmarks. Training data verified clean against all four benchmark test sets (13-gram and 8-gram overlap checks with positive-control validation).

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "kosa-labs/kosa-4B-it-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [{"role": "user", "content": "Write a concise project update."}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
```

GGUF quantizations are available in /gguf:
- gguf/kosa-4B-it-v1-Q4_K_M.gguf
- gguf/kosa-4B-it-v1-Q5_K_M.gguf
- gguf/kosa-4B-it-v1-Q8_0.gguf