Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3690,4 +3690,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3690 |
### Framework versions
|
| 3691 |
|
| 3692 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3693 |
- PEFT 0.6.2
|
|
|
|
| 3690 |
### Framework versions
|
| 3691 |
|
| 3692 |
|
| 3693 |
+
- PEFT 0.6.2
|
| 3694 |
+
## Training procedure
|
| 3695 |
+
|
| 3696 |
+
|
| 3697 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3698 |
+
- load_in_8bit: True
|
| 3699 |
+
- load_in_4bit: False
|
| 3700 |
+
- llm_int8_threshold: 6.0
|
| 3701 |
+
- llm_int8_skip_modules: None
|
| 3702 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3703 |
+
- llm_int8_has_fp16_weight: False
|
| 3704 |
+
- bnb_4bit_quant_type: fp4
|
| 3705 |
+
- bnb_4bit_use_double_quant: False
|
| 3706 |
+
- bnb_4bit_compute_dtype: float32
|
| 3707 |
+
|
| 3708 |
+
### Framework versions
|
| 3709 |
+
|
| 3710 |
+
|
| 3711 |
- 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 sha256:9bda22a116b43a1ac5b989ff786cfeaf8af535e9623c52fde76062aa8f3cde19
|
| 3 |
size 21020682
|