Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2736,4 +2736,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2736 |
### Framework versions
|
| 2737 |
|
| 2738 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2739 |
- PEFT 0.6.2
|
|
|
|
| 2736 |
### Framework versions
|
| 2737 |
|
| 2738 |
|
| 2739 |
+
- PEFT 0.6.2
|
| 2740 |
+
## Training procedure
|
| 2741 |
+
|
| 2742 |
+
|
| 2743 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2744 |
+
- load_in_8bit: True
|
| 2745 |
+
- load_in_4bit: False
|
| 2746 |
+
- llm_int8_threshold: 6.0
|
| 2747 |
+
- llm_int8_skip_modules: None
|
| 2748 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2749 |
+
- llm_int8_has_fp16_weight: False
|
| 2750 |
+
- bnb_4bit_quant_type: fp4
|
| 2751 |
+
- bnb_4bit_use_double_quant: False
|
| 2752 |
+
- bnb_4bit_compute_dtype: float32
|
| 2753 |
+
|
| 2754 |
+
### Framework versions
|
| 2755 |
+
|
| 2756 |
+
|
| 2757 |
- 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:a260cd4a4df3dd1d063ef4605cd15f6b4342a57e9312ff978b04f37b88d95f79
|
| 3 |
size 21020682
|