Text Generation
PEFT
Safetensors
English
qlora
lora
trl
sft
unsloth
theory-of-mind
tombench
social-reasoning
small-language-model
conversational
Eval Results (legacy)
Instructions to use nextmina/qwen2.5-3b-tombench-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nextmina/qwen2.5-3b-tombench-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-3B-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "nextmina/qwen2.5-3b-tombench-qlora") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Create NOTICE
Browse files
NOTICE
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This repository contains a QLoRA adapter fine-tuned from Qwen2.5-3B-Instruct,
|
| 2 |
+
developed by Alibaba Cloud (Qwen Team), and released under the Qwen Research
|
| 3 |
+
License (see LICENSE file in this repository).
|
| 4 |
+
|
| 5 |
+
Base model: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct
|