Isabelle Cudlitz
commited on
Commit
·
45d273e
1
Parent(s):
85b1fdd
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -954,4 +954,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 954 |
### Framework versions
|
| 955 |
|
| 956 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 957 |
- PEFT 0.6.2
|
|
|
|
| 954 |
### Framework versions
|
| 955 |
|
| 956 |
|
| 957 |
+
- PEFT 0.6.2
|
| 958 |
+
## Training procedure
|
| 959 |
+
|
| 960 |
+
|
| 961 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 962 |
+
- load_in_8bit: False
|
| 963 |
+
- load_in_4bit: True
|
| 964 |
+
- llm_int8_threshold: 6.0
|
| 965 |
+
- llm_int8_skip_modules: None
|
| 966 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 967 |
+
- llm_int8_has_fp16_weight: False
|
| 968 |
+
- bnb_4bit_quant_type: fp4
|
| 969 |
+
- bnb_4bit_use_double_quant: True
|
| 970 |
+
- bnb_4bit_compute_dtype: float32
|
| 971 |
+
|
| 972 |
+
### Framework versions
|
| 973 |
+
|
| 974 |
+
|
| 975 |
- 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:a58d4780ecc17e041395a60fc10c01a33947c8d2799c1aeefddd2ff2cf95b34a
|
| 3 |
size 21020682
|