Isabelle Cudlitz
commited on
Commit
·
d9d3a16
1
Parent(s):
8ed01d2
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3258,4 +3258,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3258 |
### Framework versions
|
| 3259 |
|
| 3260 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3261 |
- PEFT 0.6.2
|
|
|
|
| 3258 |
### Framework versions
|
| 3259 |
|
| 3260 |
|
| 3261 |
+
- PEFT 0.6.2
|
| 3262 |
+
## Training procedure
|
| 3263 |
+
|
| 3264 |
+
|
| 3265 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3266 |
+
- load_in_8bit: True
|
| 3267 |
+
- load_in_4bit: False
|
| 3268 |
+
- llm_int8_threshold: 6.0
|
| 3269 |
+
- llm_int8_skip_modules: None
|
| 3270 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3271 |
+
- llm_int8_has_fp16_weight: False
|
| 3272 |
+
- bnb_4bit_quant_type: fp4
|
| 3273 |
+
- bnb_4bit_use_double_quant: False
|
| 3274 |
+
- bnb_4bit_compute_dtype: float32
|
| 3275 |
+
|
| 3276 |
+
### Framework versions
|
| 3277 |
+
|
| 3278 |
+
|
| 3279 |
- 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 sha256:3f7842396e69ef174d43a8fadd4e27df084b1d85f194da336898531e9f55b997
|
| 3 |
size 21020682
|