Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2394,4 +2394,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2394 |
### Framework versions
|
| 2395 |
|
| 2396 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2397 |
- PEFT 0.6.2
|
|
|
|
| 2394 |
### Framework versions
|
| 2395 |
|
| 2396 |
|
| 2397 |
+
- PEFT 0.6.2
|
| 2398 |
+
## Training procedure
|
| 2399 |
+
|
| 2400 |
+
|
| 2401 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2402 |
+
- load_in_8bit: True
|
| 2403 |
+
- load_in_4bit: False
|
| 2404 |
+
- llm_int8_threshold: 6.0
|
| 2405 |
+
- llm_int8_skip_modules: None
|
| 2406 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2407 |
+
- llm_int8_has_fp16_weight: False
|
| 2408 |
+
- bnb_4bit_quant_type: fp4
|
| 2409 |
+
- bnb_4bit_use_double_quant: False
|
| 2410 |
+
- bnb_4bit_compute_dtype: float32
|
| 2411 |
+
|
| 2412 |
+
### Framework versions
|
| 2413 |
+
|
| 2414 |
+
|
| 2415 |
- 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 sha256:5df5d67f7879424a2f8a4b7141b238150a3f15e8dd26128ad9a3ab1ad4b65cfb
|
| 3 |
size 21020682
|