Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1062,4 +1062,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1062 |
### Framework versions
|
| 1063 |
|
| 1064 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1065 |
- PEFT 0.6.2
|
|
|
|
| 1062 |
### Framework versions
|
| 1063 |
|
| 1064 |
|
| 1065 |
+
- PEFT 0.6.2
|
| 1066 |
+
## Training procedure
|
| 1067 |
+
|
| 1068 |
+
|
| 1069 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1070 |
+
- load_in_8bit: True
|
| 1071 |
+
- load_in_4bit: False
|
| 1072 |
+
- llm_int8_threshold: 6.0
|
| 1073 |
+
- llm_int8_skip_modules: None
|
| 1074 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1075 |
+
- llm_int8_has_fp16_weight: False
|
| 1076 |
+
- bnb_4bit_quant_type: fp4
|
| 1077 |
+
- bnb_4bit_use_double_quant: False
|
| 1078 |
+
- bnb_4bit_compute_dtype: float32
|
| 1079 |
+
|
| 1080 |
+
### Framework versions
|
| 1081 |
+
|
| 1082 |
+
|
| 1083 |
- 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 sha256:0cc76cc1911473ff8b488627858813269b4aadd4fd8651c9a8a5c4d83e231ccc
|
| 3 |
size 21020682
|