LiuRuiLin
commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,7 @@
|
|
| 2 |
license: unknown
|
| 3 |
---
|
| 4 |
|
| 5 |
-
This is
|
| 6 |
-
|
| 7 |
-
**Cal Datasets:**
|
| 8 |
-
[ptb_text_only](https://huggingface.co/datasets/ptb_text_only), 128 examples, 2048 seq_len.
|
| 9 |
-
|
| 10 |
-
|
| 11 |
|
| 12 |
**Quantize config:**
|
| 13 |
"bits": 4,
|
|
@@ -19,5 +14,5 @@ This is 01-ai/Yi-6B quantized with AutoGPTQ in 4-bit.
|
|
| 19 |
"true_sequential": true,
|
| 20 |
"model_name_or_path": null,
|
| 21 |
"model_file_base_name": null,
|
| 22 |
-
"
|
| 23 |
"quant_method": "gptq"
|
|
|
|
| 2 |
license: unknown
|
| 3 |
---
|
| 4 |
|
| 5 |
+
This is TinyLlama/TinyLlama-1.1B-Chat-v1.0 quantized with AutoGPTQ in 4-bit.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
**Quantize config:**
|
| 8 |
"bits": 4,
|
|
|
|
| 14 |
"true_sequential": true,
|
| 15 |
"model_name_or_path": null,
|
| 16 |
"model_file_base_name": null,
|
| 17 |
+
"checkpoint_format": "gptq",
|
| 18 |
"quant_method": "gptq"
|