Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1224,4 +1224,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1224 |
### Framework versions
|
| 1225 |
|
| 1226 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1227 |
- PEFT 0.6.2
|
|
|
|
| 1224 |
### Framework versions
|
| 1225 |
|
| 1226 |
|
| 1227 |
+
- PEFT 0.6.2
|
| 1228 |
+
## Training procedure
|
| 1229 |
+
|
| 1230 |
+
|
| 1231 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1232 |
+
- load_in_8bit: True
|
| 1233 |
+
- load_in_4bit: False
|
| 1234 |
+
- llm_int8_threshold: 6.0
|
| 1235 |
+
- llm_int8_skip_modules: None
|
| 1236 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1237 |
+
- llm_int8_has_fp16_weight: False
|
| 1238 |
+
- bnb_4bit_quant_type: fp4
|
| 1239 |
+
- bnb_4bit_use_double_quant: False
|
| 1240 |
+
- bnb_4bit_compute_dtype: float32
|
| 1241 |
+
|
| 1242 |
+
### Framework versions
|
| 1243 |
+
|
| 1244 |
+
|
| 1245 |
- 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 sha256:816e03fe66ee4cbbdb486dabbf444c781bd9fc5461128292b558111ab7b5139d
|
| 3 |
size 21020682
|