108 lines
3.0 KiB
Markdown
108 lines
3.0 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
- it
|
|
tags:
|
|
- qwen3
|
|
- qlora
|
|
- fine-tuned
|
|
- instruction-tuning
|
|
- peft
|
|
- safetensors
|
|
library_name: peft
|
|
base_model: Qwen/Qwen3-4B-Base
|
|
---
|
|
|
|
# Nexus Plus v2
|
|
|
|
A **4.05B parameter** causal language model fine-tuned from [Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) using QLoRA on ~50k instruction examples.
|
|
|
|
## Try it Online
|
|
|
|
Test the model directly in your browser:
|
|
|
|
[](https://try-nexus-ai.streamlit.app)
|
|
[](https://github.com/JustScriptzz/nexus-smAll-web)
|
|
|
|
## Model Details
|
|
|
|
| Parameter | Value |
|
|
|-----------|-------|
|
|
| Base model | Qwen/Qwen3-4B-Base |
|
|
| Total parameters | 4.05B |
|
|
| Trainable parameters | 33M (LoRA) |
|
|
| LoRA rank | 16 |
|
|
| LoRA alpha | 32 |
|
|
| Target modules | q_proj, v_proj |
|
|
| Quantization | 4-bit (QLoRA) |
|
|
| Precision | BF16 |
|
|
|
|
## How to Use
|
|
|
|
### With PEFT (adapters only)
|
|
|
|
```python
|
|
from peft import PeftModel
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
base_model = AutoModelForCausalLM.from_pretrained(
|
|
"Qwen/Qwen3-4B-Base",
|
|
torch_dtype="auto",
|
|
device_map="auto"
|
|
)
|
|
model = PeftModel.from_pretrained(base_model, "JustScriptzz/nexus-plus-v2")
|
|
tokenizer = AutoTokenizer.from_pretrained("JustScriptzz/nexus-plus-v2")
|
|
|
|
messages = [
|
|
{"role": "user", "content": "What is Python?"}
|
|
]
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
outputs = model.generate(**inputs, max_new_tokens=512)
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
```
|
|
|
|
### Merged model (recommended)
|
|
|
|
This repo contains the fully merged model (LoRA weights baked into base). No PEFT needed:
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
"JustScriptzz/nexus-plus-v2",
|
|
torch_dtype="auto",
|
|
device_map="auto"
|
|
)
|
|
tokenizer = AutoTokenizer.from_pretrained("JustScriptzz/nexus-plus-v2")
|
|
|
|
messages = [
|
|
{"role": "user", "content": "What is Python?"}
|
|
]
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
outputs = model.generate(**inputs, max_new_tokens=512)
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
```
|
|
|
|
## Training
|
|
|
|
- **Base model**: Qwen3-4B-Base (4.05B params, 4-bit quantized)
|
|
- **Dataset**: ~50k instruction examples (Dolly-15k, synthetic QA, general instruction data)
|
|
- **Method**: QLoRA (rank 16, alpha 32, targeting q_proj and v_proj)
|
|
- **Hardware**: RTX 5060 Ti 16GB
|
|
- **Training time**: ~7 hours
|
|
- **Steps**: 5,634
|
|
- **Final loss**: 1.45
|
|
|
|
## Limitations
|
|
|
|
- Fine-tuned on a relatively small dataset
|
|
- May not generalize well to all domains
|
|
- Best used as a learning experiment or starting point for further fine-tuning
|
|
|
|
## License
|
|
|
|
Apache 2.0
|