Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1530,4 +1530,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1530 |
### Framework versions
|
| 1531 |
|
| 1532 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1533 |
- PEFT 0.6.2
|
|
|
|
| 1530 |
### Framework versions
|
| 1531 |
|
| 1532 |
|
| 1533 |
+
- PEFT 0.6.2
|
| 1534 |
+
## Training procedure
|
| 1535 |
+
|
| 1536 |
+
|
| 1537 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1538 |
+
- load_in_8bit: True
|
| 1539 |
+
- load_in_4bit: False
|
| 1540 |
+
- llm_int8_threshold: 6.0
|
| 1541 |
+
- llm_int8_skip_modules: None
|
| 1542 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1543 |
+
- llm_int8_has_fp16_weight: False
|
| 1544 |
+
- bnb_4bit_quant_type: fp4
|
| 1545 |
+
- bnb_4bit_use_double_quant: False
|
| 1546 |
+
- bnb_4bit_compute_dtype: float32
|
| 1547 |
+
|
| 1548 |
+
### Framework versions
|
| 1549 |
+
|
| 1550 |
+
|
| 1551 |
- 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:c08d8987c443638f0f1b12e97fca8e1d9ca0b03ccfc8f0d7a439ff42245fa1ea
|
| 3 |
size 21020682
|