Commit
•
d19b4cb
1
Parent(s):
142326a
Upload 3 files
Browse files
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
## Training procedure
|
| 2 |
|
| 3 |
|
|
@@ -6,7 +9,24 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 6 |
- llm_int8_threshold: 6.0
|
| 7 |
- llm_int8_skip_modules: None
|
| 8 |
- llm_int8_enable_fp32_cpu_offload: False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
### Framework versions
|
| 10 |
|
|
|
|
| 11 |
|
| 12 |
- PEFT 0.5.0.dev0
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
|
|
|
| 9 |
- llm_int8_threshold: 6.0
|
| 10 |
- llm_int8_skip_modules: None
|
| 11 |
- llm_int8_enable_fp32_cpu_offload: False
|
| 12 |
+
|
| 13 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 14 |
+
- load_in_8bit: True
|
| 15 |
+
- llm_int8_threshold: 6.0
|
| 16 |
+
- llm_int8_skip_modules: None
|
| 17 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
- PEFT 0.5.0.dev0
|
| 21 |
+
|
| 22 |
+
- PEFT 0.5.0.dev0
|
| 23 |
+
config was used during training:
|
| 24 |
+
- load_in_8bit: True
|
| 25 |
+
- llm_int8_threshold: 6.0
|
| 26 |
+
- llm_int8_skip_modules: None
|
| 27 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 28 |
### Framework versions
|
| 29 |
|
| 30 |
+
- PEFT 0.5.0.dev0
|
| 31 |
|
| 32 |
- PEFT 0.5.0.dev0
|