Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -990,4 +990,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 990 |
### Framework versions
|
| 991 |
|
| 992 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 993 |
- PEFT 0.6.2
|
|
|
|
| 990 |
### Framework versions
|
| 991 |
|
| 992 |
|
| 993 |
+
- PEFT 0.6.2
|
| 994 |
+
## Training procedure
|
| 995 |
+
|
| 996 |
+
|
| 997 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 998 |
+
- load_in_8bit: True
|
| 999 |
+
- load_in_4bit: False
|
| 1000 |
+
- llm_int8_threshold: 6.0
|
| 1001 |
+
- llm_int8_skip_modules: None
|
| 1002 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1003 |
+
- llm_int8_has_fp16_weight: False
|
| 1004 |
+
- bnb_4bit_quant_type: fp4
|
| 1005 |
+
- bnb_4bit_use_double_quant: False
|
| 1006 |
+
- bnb_4bit_compute_dtype: float32
|
| 1007 |
+
|
| 1008 |
+
### Framework versions
|
| 1009 |
+
|
| 1010 |
+
|
| 1011 |
- PEFT 0.6.2
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21020682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60692dc927208b95e04a6a056dc5f7cc84d9e1a79c779b339082c79217dc9d19
|
| 3 |
size 21020682
|