Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2016,4 +2016,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2016 |
### Framework versions
|
| 2017 |
|
| 2018 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2019 |
- PEFT 0.6.2
|
|
|
|
| 2016 |
### Framework versions
|
| 2017 |
|
| 2018 |
|
| 2019 |
+
- PEFT 0.6.2
|
| 2020 |
+
## Training procedure
|
| 2021 |
+
|
| 2022 |
+
|
| 2023 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2024 |
+
- load_in_8bit: True
|
| 2025 |
+
- load_in_4bit: False
|
| 2026 |
+
- llm_int8_threshold: 6.0
|
| 2027 |
+
- llm_int8_skip_modules: None
|
| 2028 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2029 |
+
- llm_int8_has_fp16_weight: False
|
| 2030 |
+
- bnb_4bit_quant_type: fp4
|
| 2031 |
+
- bnb_4bit_use_double_quant: False
|
| 2032 |
+
- bnb_4bit_compute_dtype: float32
|
| 2033 |
+
|
| 2034 |
+
### Framework versions
|
| 2035 |
+
|
| 2036 |
+
|
| 2037 |
- 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 sha256:1be164241cf4e0599407c50e9e4c04fb70c096a7ef830e7cb8c1768d09a088e6
|
| 3 |
size 21020682
|