Isabelle Cudlitz
commited on
Commit
·
ee563f9
1
Parent(s):
0c6656d
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3330,4 +3330,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3330 |
### Framework versions
|
| 3331 |
|
| 3332 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3333 |
- PEFT 0.6.2
|
|
|
|
| 3330 |
### Framework versions
|
| 3331 |
|
| 3332 |
|
| 3333 |
+
- PEFT 0.6.2
|
| 3334 |
+
## Training procedure
|
| 3335 |
+
|
| 3336 |
+
|
| 3337 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3338 |
+
- load_in_8bit: True
|
| 3339 |
+
- load_in_4bit: False
|
| 3340 |
+
- llm_int8_threshold: 6.0
|
| 3341 |
+
- llm_int8_skip_modules: None
|
| 3342 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3343 |
+
- llm_int8_has_fp16_weight: False
|
| 3344 |
+
- bnb_4bit_quant_type: fp4
|
| 3345 |
+
- bnb_4bit_use_double_quant: False
|
| 3346 |
+
- bnb_4bit_compute_dtype: float32
|
| 3347 |
+
|
| 3348 |
+
### Framework versions
|
| 3349 |
+
|
| 3350 |
+
|
| 3351 |
- 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 sha256:748fa23cad0aa2c33445cd78ebe14f61804b71b204d1c4b87c0b73a81c21513d
|
| 3 |
size 21020682
|