Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,10 @@ library_name: transformers
|
|
| 7 |
|
| 8 |
# Llama3_DiscoLeo_8B_DARE_Experimental_4bit_awq_glc
|
| 9 |
|
| 10 |
-
This model is a 4 bit quantization of [DiscoResearch/Llama3_DiscoLeo_8B_DARE_Experimental](https://huggingface.co/DiscoResearch/Llama3_DiscoLeo_8B_DARE_Experimental)
|
|
|
|
|
|
|
|
|
|
| 11 |
Copy of the original model card:
|
| 12 |
|
| 13 |
|
|
|
|
| 7 |
|
| 8 |
# Llama3_DiscoLeo_8B_DARE_Experimental_4bit_awq_glc
|
| 9 |
|
| 10 |
+
This model is a 4 bit quantization of [DiscoResearch/Llama3_DiscoLeo_8B_DARE_Experimental](https://huggingface.co/DiscoResearch/Llama3_DiscoLeo_8B_DARE_Experimental)
|
| 11 |
+
created using [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) with a custom bilingual calibration dataset and `quant_config = {"zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM"}`.
|
| 12 |
+
|
| 13 |
+
|
| 14 |
Copy of the original model card:
|
| 15 |
|
| 16 |
|