Upload model
Browse files- README.md +18 -0
- adapter_config.json +2 -2
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -630,4 +630,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 630 |
### Framework versions
|
| 631 |
|
| 632 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 633 |
- PEFT 0.6.2
|
|
|
|
| 630 |
### Framework versions
|
| 631 |
|
| 632 |
|
| 633 |
+
- PEFT 0.6.2
|
| 634 |
+
## Training procedure
|
| 635 |
+
|
| 636 |
+
|
| 637 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 638 |
+
- load_in_8bit: True
|
| 639 |
+
- load_in_4bit: False
|
| 640 |
+
- llm_int8_threshold: 6.0
|
| 641 |
+
- llm_int8_skip_modules: None
|
| 642 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 643 |
+
- llm_int8_has_fp16_weight: False
|
| 644 |
+
- bnb_4bit_quant_type: fp4
|
| 645 |
+
- bnb_4bit_use_double_quant: False
|
| 646 |
+
- bnb_4bit_compute_dtype: float32
|
| 647 |
+
|
| 648 |
+
### Framework versions
|
| 649 |
+
|
| 650 |
+
|
| 651 |
- PEFT 0.6.2
|
adapter_config.json
CHANGED
|
@@ -19,8 +19,8 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
],
|
| 25 |
"task_type": null
|
| 26 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"q_proj"
|
| 24 |
],
|
| 25 |
"task_type": null
|
| 26 |
}
|
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 sha256:1f1a08a1f037f7cef870a07f82d1f8593f49e46f788f065c89bd22188b49b6a0
|
| 3 |
size 21020682
|