Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4392,4 +4392,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4392 |
### Framework versions
|
| 4393 |
|
| 4394 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4395 |
- PEFT 0.6.2
|
|
|
|
| 4392 |
### Framework versions
|
| 4393 |
|
| 4394 |
|
| 4395 |
+
- PEFT 0.6.2
|
| 4396 |
+
## Training procedure
|
| 4397 |
+
|
| 4398 |
+
|
| 4399 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4400 |
+
- load_in_8bit: True
|
| 4401 |
+
- load_in_4bit: False
|
| 4402 |
+
- llm_int8_threshold: 6.0
|
| 4403 |
+
- llm_int8_skip_modules: None
|
| 4404 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4405 |
+
- llm_int8_has_fp16_weight: False
|
| 4406 |
+
- bnb_4bit_quant_type: fp4
|
| 4407 |
+
- bnb_4bit_use_double_quant: False
|
| 4408 |
+
- bnb_4bit_compute_dtype: float32
|
| 4409 |
+
|
| 4410 |
+
### Framework versions
|
| 4411 |
+
|
| 4412 |
+
|
| 4413 |
- 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:a4c9bf5756379998deb8b9f6561bad668b1b62df2569016fb9621b2636f864de
|
| 3 |
size 21020682
|