Commit ·
d065f42
1
Parent(s): 8ac321c
Upload model
Browse files- README.md +0 -12
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -26,17 +26,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 26 |
- bnb_4bit_use_double_quant: True
|
| 27 |
- bnb_4bit_compute_dtype: bfloat16
|
| 28 |
|
| 29 |
-
The following `bitsandbytes` quantization config was used during training:
|
| 30 |
-
- load_in_8bit: False
|
| 31 |
-
- load_in_4bit: True
|
| 32 |
-
- llm_int8_threshold: 6.0
|
| 33 |
-
- llm_int8_skip_modules: None
|
| 34 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
| 35 |
-
- llm_int8_has_fp16_weight: False
|
| 36 |
-
- bnb_4bit_quant_type: nf4
|
| 37 |
-
- bnb_4bit_use_double_quant: True
|
| 38 |
-
- bnb_4bit_compute_dtype: bfloat16
|
| 39 |
-
|
| 40 |
The following `bitsandbytes` quantization config was used during training:
|
| 41 |
- load_in_8bit: False
|
| 42 |
- load_in_4bit: True
|
|
@@ -49,7 +38,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 49 |
- bnb_4bit_compute_dtype: bfloat16
|
| 50 |
### Framework versions
|
| 51 |
|
| 52 |
-
- PEFT 0.5.0.dev0
|
| 53 |
- PEFT 0.5.0.dev0
|
| 54 |
- PEFT 0.5.0.dev0
|
| 55 |
|
|
|
|
| 26 |
- bnb_4bit_use_double_quant: True
|
| 27 |
- bnb_4bit_compute_dtype: bfloat16
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
The following `bitsandbytes` quantization config was used during training:
|
| 30 |
- load_in_8bit: False
|
| 31 |
- load_in_4bit: True
|
|
|
|
| 38 |
- bnb_4bit_compute_dtype: bfloat16
|
| 39 |
### Framework versions
|
| 40 |
|
|
|
|
| 41 |
- PEFT 0.5.0.dev0
|
| 42 |
- PEFT 0.5.0.dev0
|
| 43 |
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18898161
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6a14b27af2792520f2b585274c10cafc4271bfdf38afb422bee4bd766bf4024
|
| 3 |
size 18898161
|