---
license: apache-2.0
tags:
- code
- holo
- qwen
language:
- en
- code
base_model: Hcompany/Holo-3.1-9B
pipeline_tag: text-generation
---

# Holo-3.1-9B-Coder

Code-specialized adaptation of [Hcompany/Holo-3.1-9B](https://huggingface.co/Hcompany/Holo-3.1-9B).

## Evaluation

| Model | HumanEval+ pass@1 | LiveCodeBench v2 pass@1 |
|-------|-------------------|------------------------|
| Holo-3.1-9B (base) | 52.4% | 31.5% |
| Holo-3.1-9B-Coder (this model) | **65.2%** (+12.8) | **37.8%** (+6.3) |

LiveCodeBench evaluated with official [`codegen_metrics`](https://github.com/LiveCodeBench/LiveCodeBench), greedy decoding, 6s timeout. Proof: [`eval/lcb_v2_official.json`](https://huggingface.co/josephmayo/Holo-3.1-9B-Coder/resolve/main/eval/lcb_v2_official.json)

## Artifacts

| Path | Description |
|------|-------------|
| `adapter/` | LoRA adapter (r=8, alpha=16, q/v targets). |
| `model.safetensors`, `config.json`, tokenizer files | Merged base + adapter model. |
| `holo-9b-coder-Q4_K_M.gguf` | llama.cpp GGUF, Q4_K_M quantization. |
| `holo-9b-coder-Q5_K_M.gguf` | llama.cpp GGUF, Q5_K_M quantization. |
| `holo-9b-coder-Q6_K.gguf` | llama.cpp GGUF, Q6_K quantization. |

## Quantization details

Quantization was performed with [llama.cpp](https://github.com/ggml-org/llama.cpp) after merging the adapter into the base model. The GGUF files use K-quant mixture schemes.

## Loading the adapter

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "Hcompany/Holo-3.1-9B"
model = AutoModelForCausalLM.from_pretrained(base, trust_remote_code=True, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "josephmayo/Holo-3.1-9B-Coder", subfolder="adapter")
model = model.merge_and_unload()
tok = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
```

## Loading a GGUF with llama.cpp

```bash
./llama-cli -m holo-9b-coder-Q4_K_M.gguf -p "Return only executable Python code.\n\ndef factorial(n):" -n 256
```

## Base model

- **Architecture:** Qwen3.5-family text backbone (decoder-only transformer).
- **License:** Apache-2.0.
- **Original model:** [Hcompany/Holo-3.1-9B](https://huggingface.co/Hcompany/Holo-3.1-9B)

## Limitations

- Generated code should be reviewed before execution.
- The model inherits the base model's knowledge cutoff and safety profile.