---
title: bitnet_b1_58-3B-Coder
canonical_url: "https://www.modelscope.ai/models/TechxGenus-MS/bitnet_b1_58-3B-Coder"
md_url: "https://www.modelscope.ai/models/TechxGenus-MS/bitnet_b1_58-3B-Coder.md"
repository: TechxGenus-MS/bitnet_b1_58-3B-Coder
last_updated: 2025-09-22
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - BitnetForCausalLM
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 128
stars: 0
---

# bitnet_b1_58-3B-Coder

> bitnet_b1_58-3B-Coder - An open-source model by TechxGenus-MS on ModelScope. Code finetuned version of bitnetb158-3B

TechxGenus-MS/bitnet_b1_58-3B-Coder is a text-generation model on ModelScope. licensed under mit.

- **Repository**: TechxGenus-MS/bitnet_b1_58-3B-Coder
- **License**: mit
- **Tasks**: text-generation
- **Downloads**: 128
- **Stars**: 0
- **Last updated**: 2025-09-22

Source: https://www.modelscope.ai/models/TechxGenus-MS/bitnet_b1_58-3B-Coder

---

### bitnet_b1_58-3B-Coder

Code finetuned version of [bitnet_b1_58-3B](https://huggingface.co/1bitLLM/bitnet_b1_58-3B)

### Usage

```python
from tokenization_bitnet import BitnetTokenizer
from transformers import AutoModelForCausalLM
import torch
PROMPT = """### Instruction
{instruction}
### Response
"""
instruction = <Your code instruction here>
prompt = PROMPT.format(instruction=instruction)
tokenizer = BitnetTokenizer.from_pretrained(
    "TechxGenus/bitnet_b1_58-3B-Coder",
    trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
    "TechxGenus/bitnet_b1_58-3B-Coder",
    torch_dtype=torch.float16,
    device_map="auto",
)
inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=2048)
print(tokenizer.decode(outputs[0]))
```

### Note

Model may sometimes make errors, produce misleading contents, or struggle to manage tasks that are not related to coding. It has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.