Isabelle Cudlitz
commited on
Commit
·
a1dfbaf
1
Parent(s):
c0acaf5
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4140,4 +4140,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4140 |
### Framework versions
|
| 4141 |
|
| 4142 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4143 |
- PEFT 0.6.2
|
|
|
|
| 4140 |
### Framework versions
|
| 4141 |
|
| 4142 |
|
| 4143 |
+
- PEFT 0.6.2
|
| 4144 |
+
## Training procedure
|
| 4145 |
+
|
| 4146 |
+
|
| 4147 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4148 |
+
- load_in_8bit: True
|
| 4149 |
+
- load_in_4bit: False
|
| 4150 |
+
- llm_int8_threshold: 6.0
|
| 4151 |
+
- llm_int8_skip_modules: None
|
| 4152 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4153 |
+
- llm_int8_has_fp16_weight: False
|
| 4154 |
+
- bnb_4bit_quant_type: fp4
|
| 4155 |
+
- bnb_4bit_use_double_quant: False
|
| 4156 |
+
- bnb_4bit_compute_dtype: float32
|
| 4157 |
+
|
| 4158 |
+
### Framework versions
|
| 4159 |
+
|
| 4160 |
+
|
| 4161 |
- 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:af55385090f23aa1344f0802582da1db88145529e4c769995cc44e0afa523782
|
| 3 |
size 21020682
|