KallistiTMR
commited on
Commit
·
443aec2
1
Parent(s):
f6a7f81
Upload model
Browse files- README.md +24 -0
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -444,6 +444,28 @@ The following `bitsandbytes` quantization config was used during training:
|
|
444 |
- bnb_4bit_use_double_quant: False
|
445 |
- bnb_4bit_compute_dtype: float16
|
446 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
447 |
The following `bitsandbytes` quantization config was used during training:
|
448 |
- load_in_8bit: False
|
449 |
- load_in_4bit: True
|
@@ -496,5 +518,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
496 |
- PEFT 0.4.0
|
497 |
- PEFT 0.4.0
|
498 |
- PEFT 0.4.0
|
|
|
|
|
499 |
|
500 |
- PEFT 0.4.0
|
|
|
444 |
- bnb_4bit_use_double_quant: False
|
445 |
- bnb_4bit_compute_dtype: float16
|
446 |
|
447 |
+
The following `bitsandbytes` quantization config was used during training:
|
448 |
+
- load_in_8bit: False
|
449 |
+
- load_in_4bit: True
|
450 |
+
- llm_int8_threshold: 6.0
|
451 |
+
- llm_int8_skip_modules: None
|
452 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
453 |
+
- llm_int8_has_fp16_weight: False
|
454 |
+
- bnb_4bit_quant_type: nf4
|
455 |
+
- bnb_4bit_use_double_quant: False
|
456 |
+
- bnb_4bit_compute_dtype: float16
|
457 |
+
|
458 |
+
The following `bitsandbytes` quantization config was used during training:
|
459 |
+
- load_in_8bit: False
|
460 |
+
- load_in_4bit: True
|
461 |
+
- llm_int8_threshold: 6.0
|
462 |
+
- llm_int8_skip_modules: None
|
463 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
464 |
+
- llm_int8_has_fp16_weight: False
|
465 |
+
- bnb_4bit_quant_type: nf4
|
466 |
+
- bnb_4bit_use_double_quant: False
|
467 |
+
- bnb_4bit_compute_dtype: float16
|
468 |
+
|
469 |
The following `bitsandbytes` quantization config was used during training:
|
470 |
- load_in_8bit: False
|
471 |
- load_in_4bit: True
|
|
|
518 |
- PEFT 0.4.0
|
519 |
- PEFT 0.4.0
|
520 |
- PEFT 0.4.0
|
521 |
+
- PEFT 0.4.0
|
522 |
+
- PEFT 0.4.0
|
523 |
|
524 |
- PEFT 0.4.0
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134263757
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a29f489050cdba79c91d11aa742b7c12c024a61858141bbe107a617ac5e71e89
|
3 |
size 134263757
|