Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3978,4 +3978,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3978 |
### Framework versions
|
| 3979 |
|
| 3980 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3981 |
- PEFT 0.6.2
|
|
|
|
| 3978 |
### Framework versions
|
| 3979 |
|
| 3980 |
|
| 3981 |
+
- PEFT 0.6.2
|
| 3982 |
+
## Training procedure
|
| 3983 |
+
|
| 3984 |
+
|
| 3985 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3986 |
+
- load_in_8bit: True
|
| 3987 |
+
- load_in_4bit: False
|
| 3988 |
+
- llm_int8_threshold: 6.0
|
| 3989 |
+
- llm_int8_skip_modules: None
|
| 3990 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3991 |
+
- llm_int8_has_fp16_weight: False
|
| 3992 |
+
- bnb_4bit_quant_type: fp4
|
| 3993 |
+
- bnb_4bit_use_double_quant: False
|
| 3994 |
+
- bnb_4bit_compute_dtype: float32
|
| 3995 |
+
|
| 3996 |
+
### Framework versions
|
| 3997 |
+
|
| 3998 |
+
|
| 3999 |
- 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 sha256:0410633850adfa1810193343246229dc08e529b633843fd446665ba6f2991371
|
| 3 |
size 21020682
|