Isabelle Cudlitz
commited on
Commit
·
9461204
1
Parent(s):
bccc8cb
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -378,4 +378,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 378 |
### Framework versions
|
| 379 |
|
| 380 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 381 |
- PEFT 0.6.2
|
|
|
|
| 378 |
### Framework versions
|
| 379 |
|
| 380 |
|
| 381 |
+
- PEFT 0.6.2
|
| 382 |
+
## Training procedure
|
| 383 |
+
|
| 384 |
+
|
| 385 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 386 |
+
- load_in_8bit: False
|
| 387 |
+
- load_in_4bit: True
|
| 388 |
+
- llm_int8_threshold: 6.0
|
| 389 |
+
- llm_int8_skip_modules: None
|
| 390 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 391 |
+
- llm_int8_has_fp16_weight: False
|
| 392 |
+
- bnb_4bit_quant_type: fp4
|
| 393 |
+
- bnb_4bit_use_double_quant: True
|
| 394 |
+
- bnb_4bit_compute_dtype: float32
|
| 395 |
+
|
| 396 |
+
### Framework versions
|
| 397 |
+
|
| 398 |
+
|
| 399 |
- 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 sha256:00baeb954a974c4beb1397e0cacf09cdeb1dc9b58d83e14ad98c9847c6d52323
|
| 3 |
size 21020682
|