Commit
·
832a5eb
1
Parent(s):
7e66269
Upload model
Browse files- README.md +24 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -708,6 +708,28 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 708 |
- bnb_4bit_use_double_quant: False
|
| 709 |
- bnb_4bit_compute_dtype: float16
|
| 710 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 711 |
The following `bitsandbytes` quantization config was used during training:
|
| 712 |
- load_in_8bit: False
|
| 713 |
- load_in_4bit: True
|
|
@@ -784,5 +806,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 784 |
- PEFT 0.4.0
|
| 785 |
- PEFT 0.4.0
|
| 786 |
- PEFT 0.4.0
|
|
|
|
|
|
|
| 787 |
|
| 788 |
- PEFT 0.4.0
|
|
|
|
| 708 |
- bnb_4bit_use_double_quant: False
|
| 709 |
- bnb_4bit_compute_dtype: float16
|
| 710 |
|
| 711 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 712 |
+
- load_in_8bit: False
|
| 713 |
+
- load_in_4bit: True
|
| 714 |
+
- llm_int8_threshold: 6.0
|
| 715 |
+
- llm_int8_skip_modules: None
|
| 716 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 717 |
+
- llm_int8_has_fp16_weight: False
|
| 718 |
+
- bnb_4bit_quant_type: nf4
|
| 719 |
+
- bnb_4bit_use_double_quant: False
|
| 720 |
+
- bnb_4bit_compute_dtype: float16
|
| 721 |
+
|
| 722 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 723 |
+
- load_in_8bit: False
|
| 724 |
+
- load_in_4bit: True
|
| 725 |
+
- llm_int8_threshold: 6.0
|
| 726 |
+
- llm_int8_skip_modules: None
|
| 727 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 728 |
+
- llm_int8_has_fp16_weight: False
|
| 729 |
+
- bnb_4bit_quant_type: nf4
|
| 730 |
+
- bnb_4bit_use_double_quant: False
|
| 731 |
+
- bnb_4bit_compute_dtype: float16
|
| 732 |
+
|
| 733 |
The following `bitsandbytes` quantization config was used during training:
|
| 734 |
- load_in_8bit: False
|
| 735 |
- load_in_4bit: True
|
|
|
|
| 806 |
- PEFT 0.4.0
|
| 807 |
- PEFT 0.4.0
|
| 808 |
- PEFT 0.4.0
|
| 809 |
+
- PEFT 0.4.0
|
| 810 |
+
- PEFT 0.4.0
|
| 811 |
|
| 812 |
- 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 sha256:7bfb296cea0a127e5697a88608c62b0d227b457e3166716101b5fc07474d53cb
|
| 3 |
size 134263757
|