Isabelle Cudlitz
commited on
Commit
·
57262d6
1
Parent(s):
f93aa21
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1098,4 +1098,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1098 |
### Framework versions
|
| 1099 |
|
| 1100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1101 |
- PEFT 0.6.2
|
|
|
|
| 1098 |
### Framework versions
|
| 1099 |
|
| 1100 |
|
| 1101 |
+
- PEFT 0.6.2
|
| 1102 |
+
## Training procedure
|
| 1103 |
+
|
| 1104 |
+
|
| 1105 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1106 |
+
- load_in_8bit: True
|
| 1107 |
+
- load_in_4bit: False
|
| 1108 |
+
- llm_int8_threshold: 6.0
|
| 1109 |
+
- llm_int8_skip_modules: None
|
| 1110 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1111 |
+
- llm_int8_has_fp16_weight: False
|
| 1112 |
+
- bnb_4bit_quant_type: fp4
|
| 1113 |
+
- bnb_4bit_use_double_quant: False
|
| 1114 |
+
- bnb_4bit_compute_dtype: float32
|
| 1115 |
+
|
| 1116 |
+
### Framework versions
|
| 1117 |
+
|
| 1118 |
+
|
| 1119 |
- 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 sha256:7e527e3b427580a4bc3fe32572eca1341342dea5175fa7b4e30f884e1c3a1b22
|
| 3 |
size 21020682
|