Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4536,4 +4536,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4536 |
### Framework versions
|
| 4537 |
|
| 4538 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4539 |
- PEFT 0.6.2
|
|
|
|
| 4536 |
### Framework versions
|
| 4537 |
|
| 4538 |
|
| 4539 |
+
- PEFT 0.6.2
|
| 4540 |
+
## Training procedure
|
| 4541 |
+
|
| 4542 |
+
|
| 4543 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4544 |
+
- load_in_8bit: True
|
| 4545 |
+
- load_in_4bit: False
|
| 4546 |
+
- llm_int8_threshold: 6.0
|
| 4547 |
+
- llm_int8_skip_modules: None
|
| 4548 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4549 |
+
- llm_int8_has_fp16_weight: False
|
| 4550 |
+
- bnb_4bit_quant_type: fp4
|
| 4551 |
+
- bnb_4bit_use_double_quant: False
|
| 4552 |
+
- bnb_4bit_compute_dtype: float32
|
| 4553 |
+
|
| 4554 |
+
### Framework versions
|
| 4555 |
+
|
| 4556 |
+
|
| 4557 |
- 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 sha256:01548dcccc4cd647942fda21bd1e61de356fa4bf2720eccd36ec47d555897022
|
| 3 |
size 21020682
|