Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2358,4 +2358,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2358 |
### Framework versions
|
| 2359 |
|
| 2360 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2361 |
- PEFT 0.6.2
|
|
|
|
| 2358 |
### Framework versions
|
| 2359 |
|
| 2360 |
|
| 2361 |
+
- PEFT 0.6.2
|
| 2362 |
+
## Training procedure
|
| 2363 |
+
|
| 2364 |
+
|
| 2365 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2366 |
+
- load_in_8bit: True
|
| 2367 |
+
- load_in_4bit: False
|
| 2368 |
+
- llm_int8_threshold: 6.0
|
| 2369 |
+
- llm_int8_skip_modules: None
|
| 2370 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2371 |
+
- llm_int8_has_fp16_weight: False
|
| 2372 |
+
- bnb_4bit_quant_type: fp4
|
| 2373 |
+
- bnb_4bit_use_double_quant: False
|
| 2374 |
+
- bnb_4bit_compute_dtype: float32
|
| 2375 |
+
|
| 2376 |
+
### Framework versions
|
| 2377 |
+
|
| 2378 |
+
|
| 2379 |
- 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:c5302d70fe4e12661c0dfea515148e4119b1d255cb466152ac1173e1763d493a
|
| 3 |
size 21020682
|