Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2052,4 +2052,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2052 |
### Framework versions
|
| 2053 |
|
| 2054 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2055 |
- PEFT 0.6.2
|
|
|
|
| 2052 |
### Framework versions
|
| 2053 |
|
| 2054 |
|
| 2055 |
+
- PEFT 0.6.2
|
| 2056 |
+
## Training procedure
|
| 2057 |
+
|
| 2058 |
+
|
| 2059 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2060 |
+
- load_in_8bit: True
|
| 2061 |
+
- load_in_4bit: False
|
| 2062 |
+
- llm_int8_threshold: 6.0
|
| 2063 |
+
- llm_int8_skip_modules: None
|
| 2064 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2065 |
+
- llm_int8_has_fp16_weight: False
|
| 2066 |
+
- bnb_4bit_quant_type: fp4
|
| 2067 |
+
- bnb_4bit_use_double_quant: False
|
| 2068 |
+
- bnb_4bit_compute_dtype: float32
|
| 2069 |
+
|
| 2070 |
+
### Framework versions
|
| 2071 |
+
|
| 2072 |
+
|
| 2073 |
- 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:a3dd8f5d7d2c18b98de5da06902cf5aa4d5c86c3d99112ece0dd648214c391b6
|
| 3 |
size 21020682
|