Downloads · 30 days
45
5% of all-time downloads
laabamone/laabam-ai-3b-v1
laabam-ai-3b-v1 is a text generation model from laabamone. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
A multilingual AI assistant fine-tuned from Qwen2.5-3B-Instruct using QLoRA.
Downloads · 30 days
45
5% of all-time downloads
All-time downloads
862
Public
Parameters
3.1B
25 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors6.4 GB · 99%
From the Hugging Face model README
A multilingual AI assistant fine-tuned from Qwen2.5-3B-Instruct using QLoRA.
| Epoch | Dataset Size | Learning Rate | Focus |
|---|---|---|---|
| 1 | 36K | 2e-4 | Core instruction following |
| 2 | 36K | 5e-5 | Continued refinement |
| 3 | 98K | 2e-5 | Expanded: safety, Indic languages, clean instructions |
| 4 | 98K | 1e-5 | Careful refinement (low LR, anti-forgetting) |
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("laabamone/laabam-ai-3b-v1")
tokenizer = AutoTokenizer.from_pretrained("laabamone/laabam-ai-3b-v1")
messages = [{"role": "user", "content": "Hello, who are you?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Apache 2.0