Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1080,4 +1080,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1080 |
### Framework versions
|
| 1081 |
|
| 1082 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1083 |
- PEFT 0.6.2
|
|
|
|
| 1080 |
### Framework versions
|
| 1081 |
|
| 1082 |
|
| 1083 |
+
- PEFT 0.6.2
|
| 1084 |
+
## Training procedure
|
| 1085 |
+
|
| 1086 |
+
|
| 1087 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1088 |
+
- load_in_8bit: True
|
| 1089 |
+
- load_in_4bit: False
|
| 1090 |
+
- llm_int8_threshold: 6.0
|
| 1091 |
+
- llm_int8_skip_modules: None
|
| 1092 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1093 |
+
- llm_int8_has_fp16_weight: False
|
| 1094 |
+
- bnb_4bit_quant_type: fp4
|
| 1095 |
+
- bnb_4bit_use_double_quant: False
|
| 1096 |
+
- bnb_4bit_compute_dtype: float32
|
| 1097 |
+
|
| 1098 |
+
### Framework versions
|
| 1099 |
+
|
| 1100 |
+
|
| 1101 |
- 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:d0fd40fc69b470061526433995d1120f2ba4a8f03fc8a30cc30f772efd02754c
|
| 3 |
size 21020682
|