Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3096,4 +3096,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3096 |
### Framework versions
|
| 3097 |
|
| 3098 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3099 |
- PEFT 0.6.2
|
|
|
|
| 3096 |
### Framework versions
|
| 3097 |
|
| 3098 |
|
| 3099 |
+
- PEFT 0.6.2
|
| 3100 |
+
## Training procedure
|
| 3101 |
+
|
| 3102 |
+
|
| 3103 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3104 |
+
- load_in_8bit: True
|
| 3105 |
+
- load_in_4bit: False
|
| 3106 |
+
- llm_int8_threshold: 6.0
|
| 3107 |
+
- llm_int8_skip_modules: None
|
| 3108 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3109 |
+
- llm_int8_has_fp16_weight: False
|
| 3110 |
+
- bnb_4bit_quant_type: fp4
|
| 3111 |
+
- bnb_4bit_use_double_quant: False
|
| 3112 |
+
- bnb_4bit_compute_dtype: float32
|
| 3113 |
+
|
| 3114 |
+
### Framework versions
|
| 3115 |
+
|
| 3116 |
+
|
| 3117 |
- 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 sha256:44e4f19f9273c044e920ad9697ce02187b01423101210c71fa826d7bbb665f64
|
| 3 |
size 21020682
|