Isabelle Cudlitz
commited on
Commit
·
a8a70fe
1
Parent(s):
2917d04
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4446,4 +4446,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4446 |
### Framework versions
|
| 4447 |
|
| 4448 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4449 |
- PEFT 0.6.2
|
|
|
|
| 4446 |
### Framework versions
|
| 4447 |
|
| 4448 |
|
| 4449 |
+
- PEFT 0.6.2
|
| 4450 |
+
## Training procedure
|
| 4451 |
+
|
| 4452 |
+
|
| 4453 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4454 |
+
- load_in_8bit: True
|
| 4455 |
+
- load_in_4bit: False
|
| 4456 |
+
- llm_int8_threshold: 6.0
|
| 4457 |
+
- llm_int8_skip_modules: None
|
| 4458 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4459 |
+
- llm_int8_has_fp16_weight: False
|
| 4460 |
+
- bnb_4bit_quant_type: fp4
|
| 4461 |
+
- bnb_4bit_use_double_quant: False
|
| 4462 |
+
- bnb_4bit_compute_dtype: float32
|
| 4463 |
+
|
| 4464 |
+
### Framework versions
|
| 4465 |
+
|
| 4466 |
+
|
| 4467 |
- 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 sha256:7ffadfab392d6e0020c0f9038351d35f60dfbf1f994361f43b8746ba4ca2d25a
|
| 3 |
size 21020682
|