Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3294,4 +3294,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3294 |
### Framework versions
|
| 3295 |
|
| 3296 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3297 |
- PEFT 0.6.2
|
|
|
|
| 3294 |
### Framework versions
|
| 3295 |
|
| 3296 |
|
| 3297 |
+
- PEFT 0.6.2
|
| 3298 |
+
## Training procedure
|
| 3299 |
+
|
| 3300 |
+
|
| 3301 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3302 |
+
- load_in_8bit: True
|
| 3303 |
+
- load_in_4bit: False
|
| 3304 |
+
- llm_int8_threshold: 6.0
|
| 3305 |
+
- llm_int8_skip_modules: None
|
| 3306 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3307 |
+
- llm_int8_has_fp16_weight: False
|
| 3308 |
+
- bnb_4bit_quant_type: fp4
|
| 3309 |
+
- bnb_4bit_use_double_quant: False
|
| 3310 |
+
- bnb_4bit_compute_dtype: float32
|
| 3311 |
+
|
| 3312 |
+
### Framework versions
|
| 3313 |
+
|
| 3314 |
+
|
| 3315 |
- 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:ebd267299fdac0555bf163896cd3d9fd9ee9407588d8969b3a1668778063ca4b
|
| 3 |
size 21020682
|