Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3492,4 +3492,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3492 |
### Framework versions
|
| 3493 |
|
| 3494 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3495 |
- PEFT 0.6.2
|
|
|
|
| 3492 |
### Framework versions
|
| 3493 |
|
| 3494 |
|
| 3495 |
+
- PEFT 0.6.2
|
| 3496 |
+
## Training procedure
|
| 3497 |
+
|
| 3498 |
+
|
| 3499 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3500 |
+
- load_in_8bit: True
|
| 3501 |
+
- load_in_4bit: False
|
| 3502 |
+
- llm_int8_threshold: 6.0
|
| 3503 |
+
- llm_int8_skip_modules: None
|
| 3504 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3505 |
+
- llm_int8_has_fp16_weight: False
|
| 3506 |
+
- bnb_4bit_quant_type: fp4
|
| 3507 |
+
- bnb_4bit_use_double_quant: False
|
| 3508 |
+
- bnb_4bit_compute_dtype: float32
|
| 3509 |
+
|
| 3510 |
+
### Framework versions
|
| 3511 |
+
|
| 3512 |
+
|
| 3513 |
- 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:aaffbd92a4cfeedf344ce74076ddd3c214a19856dd92be9acd8aad36a6acaa4e
|
| 3 |
size 21020682
|