Isabelle Cudlitz
commited on
Commit
·
bccc8cb
1
Parent(s):
2547d3b
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -360,4 +360,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 360 |
### Framework versions
|
| 361 |
|
| 362 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 363 |
- PEFT 0.6.2
|
|
|
|
| 360 |
### Framework versions
|
| 361 |
|
| 362 |
|
| 363 |
+
- PEFT 0.6.2
|
| 364 |
+
## Training procedure
|
| 365 |
+
|
| 366 |
+
|
| 367 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 368 |
+
- load_in_8bit: False
|
| 369 |
+
- load_in_4bit: True
|
| 370 |
+
- llm_int8_threshold: 6.0
|
| 371 |
+
- llm_int8_skip_modules: None
|
| 372 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 373 |
+
- llm_int8_has_fp16_weight: False
|
| 374 |
+
- bnb_4bit_quant_type: fp4
|
| 375 |
+
- bnb_4bit_use_double_quant: True
|
| 376 |
+
- bnb_4bit_compute_dtype: float32
|
| 377 |
+
|
| 378 |
+
### Framework versions
|
| 379 |
+
|
| 380 |
+
|
| 381 |
- 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 sha256:3a78b1359068de048916c0f7608ad2429b6380a305f501461aac692af8da2e54
|
| 3 |
size 21020682
|