Upload model
Browse files- README.md +1 -1
- adapter_model.bin +2 -2
README.md
CHANGED
|
@@ -13,7 +13,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 13 |
- llm_int8_has_fp16_weight: False
|
| 14 |
- bnb_4bit_quant_type: nf4
|
| 15 |
- bnb_4bit_use_double_quant: True
|
| 16 |
-
- bnb_4bit_compute_dtype:
|
| 17 |
### Framework versions
|
| 18 |
|
| 19 |
|
|
|
|
| 13 |
- llm_int8_has_fp16_weight: False
|
| 14 |
- bnb_4bit_quant_type: nf4
|
| 15 |
- bnb_4bit_use_double_quant: True
|
| 16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 17 |
### Framework versions
|
| 18 |
|
| 19 |
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:701d7227ee38a3c308fdd773360bc48c26fa03c6796ae109b9634090c41765f2
|
| 3 |
+
size 66892138
|