Isabelle Cudlitz
commited on
Commit
·
fab3c3f
1
Parent(s):
bd4066f
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -432,4 +432,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 432 |
### Framework versions
|
| 433 |
|
| 434 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 435 |
- PEFT 0.6.2
|
|
|
|
| 432 |
### Framework versions
|
| 433 |
|
| 434 |
|
| 435 |
+
- PEFT 0.6.2
|
| 436 |
+
## Training procedure
|
| 437 |
+
|
| 438 |
+
|
| 439 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 440 |
+
- load_in_8bit: False
|
| 441 |
+
- load_in_4bit: True
|
| 442 |
+
- llm_int8_threshold: 6.0
|
| 443 |
+
- llm_int8_skip_modules: None
|
| 444 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 445 |
+
- llm_int8_has_fp16_weight: False
|
| 446 |
+
- bnb_4bit_quant_type: fp4
|
| 447 |
+
- bnb_4bit_use_double_quant: True
|
| 448 |
+
- bnb_4bit_compute_dtype: float32
|
| 449 |
+
|
| 450 |
+
### Framework versions
|
| 451 |
+
|
| 452 |
+
|
| 453 |
- 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:f0b1a979f8a6f0793557d3295528843872e8f7e964f3d344d7d28ca611351ffd
|
| 3 |
size 21020682
|