Isabelle Cudlitz
commited on
Commit
·
ab6a5f6
1
Parent(s):
7a92f8d
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3384,4 +3384,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3384 |
### Framework versions
|
| 3385 |
|
| 3386 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3387 |
- PEFT 0.6.2
|
|
|
|
| 3384 |
### Framework versions
|
| 3385 |
|
| 3386 |
|
| 3387 |
+
- PEFT 0.6.2
|
| 3388 |
+
## Training procedure
|
| 3389 |
+
|
| 3390 |
+
|
| 3391 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3392 |
+
- load_in_8bit: True
|
| 3393 |
+
- load_in_4bit: False
|
| 3394 |
+
- llm_int8_threshold: 6.0
|
| 3395 |
+
- llm_int8_skip_modules: None
|
| 3396 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3397 |
+
- llm_int8_has_fp16_weight: False
|
| 3398 |
+
- bnb_4bit_quant_type: fp4
|
| 3399 |
+
- bnb_4bit_use_double_quant: False
|
| 3400 |
+
- bnb_4bit_compute_dtype: float32
|
| 3401 |
+
|
| 3402 |
+
### Framework versions
|
| 3403 |
+
|
| 3404 |
+
|
| 3405 |
- 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 sha256:8286d8e997ff39d614ff8fd23e0ac44c00984bae63ae8949b249df97e6450be3
|
| 3 |
size 21020682
|