Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2268,4 +2268,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2268 |
### Framework versions
|
| 2269 |
|
| 2270 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2271 |
- PEFT 0.6.2
|
|
|
|
| 2268 |
### Framework versions
|
| 2269 |
|
| 2270 |
|
| 2271 |
+
- PEFT 0.6.2
|
| 2272 |
+
## Training procedure
|
| 2273 |
+
|
| 2274 |
+
|
| 2275 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2276 |
+
- load_in_8bit: True
|
| 2277 |
+
- load_in_4bit: False
|
| 2278 |
+
- llm_int8_threshold: 6.0
|
| 2279 |
+
- llm_int8_skip_modules: None
|
| 2280 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2281 |
+
- llm_int8_has_fp16_weight: False
|
| 2282 |
+
- bnb_4bit_quant_type: fp4
|
| 2283 |
+
- bnb_4bit_use_double_quant: False
|
| 2284 |
+
- bnb_4bit_compute_dtype: float32
|
| 2285 |
+
|
| 2286 |
+
### Framework versions
|
| 2287 |
+
|
| 2288 |
+
|
| 2289 |
- 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 sha256:8021c0df63420893de6f30a6323c956bdf00180200bf8c22f78d1d4d946f872f
|
| 3 |
size 21020682
|