Isabelle Cudlitz
commited on
Commit
·
b753549
1
Parent(s):
fbb1b7f
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4194,4 +4194,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4194 |
### Framework versions
|
| 4195 |
|
| 4196 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4197 |
- PEFT 0.6.2
|
|
|
|
| 4194 |
### Framework versions
|
| 4195 |
|
| 4196 |
|
| 4197 |
+
- PEFT 0.6.2
|
| 4198 |
+
## Training procedure
|
| 4199 |
+
|
| 4200 |
+
|
| 4201 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4202 |
+
- load_in_8bit: True
|
| 4203 |
+
- load_in_4bit: False
|
| 4204 |
+
- llm_int8_threshold: 6.0
|
| 4205 |
+
- llm_int8_skip_modules: None
|
| 4206 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4207 |
+
- llm_int8_has_fp16_weight: False
|
| 4208 |
+
- bnb_4bit_quant_type: fp4
|
| 4209 |
+
- bnb_4bit_use_double_quant: False
|
| 4210 |
+
- bnb_4bit_compute_dtype: float32
|
| 4211 |
+
|
| 4212 |
+
### Framework versions
|
| 4213 |
+
|
| 4214 |
+
|
| 4215 |
- 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 sha256:0a375c0b7bb045ee95feaabe1c292609445b36639648fcd138f6381a55de9691
|
| 3 |
size 21020682
|