Isabelle Cudlitz
commited on
Commit
·
990af4a
1
Parent(s):
ab6a5f6
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3402,4 +3402,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3402 |
### Framework versions
|
| 3403 |
|
| 3404 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3405 |
- PEFT 0.6.2
|
|
|
|
| 3402 |
### Framework versions
|
| 3403 |
|
| 3404 |
|
| 3405 |
+
- PEFT 0.6.2
|
| 3406 |
+
## Training procedure
|
| 3407 |
+
|
| 3408 |
+
|
| 3409 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3410 |
+
- load_in_8bit: True
|
| 3411 |
+
- load_in_4bit: False
|
| 3412 |
+
- llm_int8_threshold: 6.0
|
| 3413 |
+
- llm_int8_skip_modules: None
|
| 3414 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3415 |
+
- llm_int8_has_fp16_weight: False
|
| 3416 |
+
- bnb_4bit_quant_type: fp4
|
| 3417 |
+
- bnb_4bit_use_double_quant: False
|
| 3418 |
+
- bnb_4bit_compute_dtype: float32
|
| 3419 |
+
|
| 3420 |
+
### Framework versions
|
| 3421 |
+
|
| 3422 |
+
|
| 3423 |
- 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:dfe7ab29d571919bec703901e177a325003dee063f63bb9b06beb60185531058
|
| 3 |
size 21020682
|