Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3420,4 +3420,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3420 |
### Framework versions
|
| 3421 |
|
| 3422 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3423 |
- PEFT 0.6.2
|
|
|
|
| 3420 |
### Framework versions
|
| 3421 |
|
| 3422 |
|
| 3423 |
+
- PEFT 0.6.2
|
| 3424 |
+
## Training procedure
|
| 3425 |
+
|
| 3426 |
+
|
| 3427 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3428 |
+
- load_in_8bit: True
|
| 3429 |
+
- load_in_4bit: False
|
| 3430 |
+
- llm_int8_threshold: 6.0
|
| 3431 |
+
- llm_int8_skip_modules: None
|
| 3432 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3433 |
+
- llm_int8_has_fp16_weight: False
|
| 3434 |
+
- bnb_4bit_quant_type: fp4
|
| 3435 |
+
- bnb_4bit_use_double_quant: False
|
| 3436 |
+
- bnb_4bit_compute_dtype: float32
|
| 3437 |
+
|
| 3438 |
+
### Framework versions
|
| 3439 |
+
|
| 3440 |
+
|
| 3441 |
- 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 sha256:75d49cb0536a9e7d8d5d98080ba1ade8b854ecddb18b60efea4b9c05f09ee56b
|
| 3 |
size 21020682
|