Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3474,4 +3474,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3474 |
### Framework versions
|
| 3475 |
|
| 3476 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3477 |
- PEFT 0.6.2
|
|
|
|
| 3474 |
### Framework versions
|
| 3475 |
|
| 3476 |
|
| 3477 |
+
- PEFT 0.6.2
|
| 3478 |
+
## Training procedure
|
| 3479 |
+
|
| 3480 |
+
|
| 3481 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3482 |
+
- load_in_8bit: True
|
| 3483 |
+
- load_in_4bit: False
|
| 3484 |
+
- llm_int8_threshold: 6.0
|
| 3485 |
+
- llm_int8_skip_modules: None
|
| 3486 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3487 |
+
- llm_int8_has_fp16_weight: False
|
| 3488 |
+
- bnb_4bit_quant_type: fp4
|
| 3489 |
+
- bnb_4bit_use_double_quant: False
|
| 3490 |
+
- bnb_4bit_compute_dtype: float32
|
| 3491 |
+
|
| 3492 |
+
### Framework versions
|
| 3493 |
+
|
| 3494 |
+
|
| 3495 |
- 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:f9ecedaa5ee32345085c855e5744fb7ed412e4ef5e00a65d741b6ebb9a8d66cf
|
| 3 |
size 21020682
|