Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2160,4 +2160,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2160 |
### Framework versions
|
| 2161 |
|
| 2162 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2163 |
- PEFT 0.6.2
|
|
|
|
| 2160 |
### Framework versions
|
| 2161 |
|
| 2162 |
|
| 2163 |
+
- PEFT 0.6.2
|
| 2164 |
+
## Training procedure
|
| 2165 |
+
|
| 2166 |
+
|
| 2167 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2168 |
+
- load_in_8bit: True
|
| 2169 |
+
- load_in_4bit: False
|
| 2170 |
+
- llm_int8_threshold: 6.0
|
| 2171 |
+
- llm_int8_skip_modules: None
|
| 2172 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2173 |
+
- llm_int8_has_fp16_weight: False
|
| 2174 |
+
- bnb_4bit_quant_type: fp4
|
| 2175 |
+
- bnb_4bit_use_double_quant: False
|
| 2176 |
+
- bnb_4bit_compute_dtype: float32
|
| 2177 |
+
|
| 2178 |
+
### Framework versions
|
| 2179 |
+
|
| 2180 |
+
|
| 2181 |
- 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:b2ab908b208964d8628fd340746a44ea3fc81eb942e40127804e602fff87b7e4
|
| 3 |
size 21020682
|