Instructions to use hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf") model = PeftModel.from_pretrained(base_model, "hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ It requires at least 20GB GRAM at inference.
|
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
|
| 37 |
-
This model is fine-tuned using
|
| 38 |
|
| 39 |
## Usage
|
| 40 |
|
|
|
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
|
| 37 |
+
This model is fine-tuned using 2,000 examples of the Alpaca-GPT4 and Glaive-function-calling-v2 datasets.
|
| 38 |
|
| 39 |
## Usage
|
| 40 |
|