Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2412,4 +2412,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2412 |
### Framework versions
|
| 2413 |
|
| 2414 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2415 |
- PEFT 0.6.2
|
|
|
|
| 2412 |
### Framework versions
|
| 2413 |
|
| 2414 |
|
| 2415 |
+
- PEFT 0.6.2
|
| 2416 |
+
## Training procedure
|
| 2417 |
+
|
| 2418 |
+
|
| 2419 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2420 |
+
- load_in_8bit: True
|
| 2421 |
+
- load_in_4bit: False
|
| 2422 |
+
- llm_int8_threshold: 6.0
|
| 2423 |
+
- llm_int8_skip_modules: None
|
| 2424 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2425 |
+
- llm_int8_has_fp16_weight: False
|
| 2426 |
+
- bnb_4bit_quant_type: fp4
|
| 2427 |
+
- bnb_4bit_use_double_quant: False
|
| 2428 |
+
- bnb_4bit_compute_dtype: float32
|
| 2429 |
+
|
| 2430 |
+
### Framework versions
|
| 2431 |
+
|
| 2432 |
+
|
| 2433 |
- 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 sha256:98c21ecc7700df9afde17fce3613172594418955e274acc3b5ca821499ed6c42
|
| 3 |
size 21020682
|