Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2034,4 +2034,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2034 |
### Framework versions
|
| 2035 |
|
| 2036 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2037 |
- PEFT 0.6.2
|
|
|
|
| 2034 |
### Framework versions
|
| 2035 |
|
| 2036 |
|
| 2037 |
+
- PEFT 0.6.2
|
| 2038 |
+
## Training procedure
|
| 2039 |
+
|
| 2040 |
+
|
| 2041 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2042 |
+
- load_in_8bit: True
|
| 2043 |
+
- load_in_4bit: False
|
| 2044 |
+
- llm_int8_threshold: 6.0
|
| 2045 |
+
- llm_int8_skip_modules: None
|
| 2046 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2047 |
+
- llm_int8_has_fp16_weight: False
|
| 2048 |
+
- bnb_4bit_quant_type: fp4
|
| 2049 |
+
- bnb_4bit_use_double_quant: False
|
| 2050 |
+
- bnb_4bit_compute_dtype: float32
|
| 2051 |
+
|
| 2052 |
+
### Framework versions
|
| 2053 |
+
|
| 2054 |
+
|
| 2055 |
- 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 sha256:923010d3157f91b1c05c51c278082c4151949a3f1c233de7e6ade213e9385805
|
| 3 |
size 21020682
|