Isabelle Cudlitz
commited on
Commit
·
d0b5f53
1
Parent(s):
cbffcfa
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4068,4 +4068,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4068 |
### Framework versions
|
| 4069 |
|
| 4070 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4071 |
- PEFT 0.6.2
|
|
|
|
| 4068 |
### Framework versions
|
| 4069 |
|
| 4070 |
|
| 4071 |
+
- PEFT 0.6.2
|
| 4072 |
+
## Training procedure
|
| 4073 |
+
|
| 4074 |
+
|
| 4075 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4076 |
+
- load_in_8bit: True
|
| 4077 |
+
- load_in_4bit: False
|
| 4078 |
+
- llm_int8_threshold: 6.0
|
| 4079 |
+
- llm_int8_skip_modules: None
|
| 4080 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4081 |
+
- llm_int8_has_fp16_weight: False
|
| 4082 |
+
- bnb_4bit_quant_type: fp4
|
| 4083 |
+
- bnb_4bit_use_double_quant: False
|
| 4084 |
+
- bnb_4bit_compute_dtype: float32
|
| 4085 |
+
|
| 4086 |
+
### Framework versions
|
| 4087 |
+
|
| 4088 |
+
|
| 4089 |
- 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:a606b733595ab76a94aeca1f826478caff6a5314b5d6a7352fa965d75381b030
|
| 3 |
size 21020682
|