Isabelle Cudlitz
commited on
Commit
·
6e49c18
1
Parent(s):
de2f183
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4266,4 +4266,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4266 |
### Framework versions
|
| 4267 |
|
| 4268 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4269 |
- PEFT 0.6.2
|
|
|
|
| 4266 |
### Framework versions
|
| 4267 |
|
| 4268 |
|
| 4269 |
+
- PEFT 0.6.2
|
| 4270 |
+
## Training procedure
|
| 4271 |
+
|
| 4272 |
+
|
| 4273 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4274 |
+
- load_in_8bit: True
|
| 4275 |
+
- load_in_4bit: False
|
| 4276 |
+
- llm_int8_threshold: 6.0
|
| 4277 |
+
- llm_int8_skip_modules: None
|
| 4278 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4279 |
+
- llm_int8_has_fp16_weight: False
|
| 4280 |
+
- bnb_4bit_quant_type: fp4
|
| 4281 |
+
- bnb_4bit_use_double_quant: False
|
| 4282 |
+
- bnb_4bit_compute_dtype: float32
|
| 4283 |
+
|
| 4284 |
+
### Framework versions
|
| 4285 |
+
|
| 4286 |
+
|
| 4287 |
- 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:bce918934f3d82b405dfd1ac2bd221303da2883fc66a50db3f8791ad95b866c4
|
| 3 |
size 21020682
|