Isabelle Cudlitz
commited on
Commit
·
3733df2
1
Parent(s):
b753549
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4212,4 +4212,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4212 |
### Framework versions
|
| 4213 |
|
| 4214 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4215 |
- PEFT 0.6.2
|
|
|
|
| 4212 |
### Framework versions
|
| 4213 |
|
| 4214 |
|
| 4215 |
+
- PEFT 0.6.2
|
| 4216 |
+
## Training procedure
|
| 4217 |
+
|
| 4218 |
+
|
| 4219 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4220 |
+
- load_in_8bit: True
|
| 4221 |
+
- load_in_4bit: False
|
| 4222 |
+
- llm_int8_threshold: 6.0
|
| 4223 |
+
- llm_int8_skip_modules: None
|
| 4224 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4225 |
+
- llm_int8_has_fp16_weight: False
|
| 4226 |
+
- bnb_4bit_quant_type: fp4
|
| 4227 |
+
- bnb_4bit_use_double_quant: False
|
| 4228 |
+
- bnb_4bit_compute_dtype: float32
|
| 4229 |
+
|
| 4230 |
+
### Framework versions
|
| 4231 |
+
|
| 4232 |
+
|
| 4233 |
- 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 sha256:169dc4ec8f3b57ffdf88ce892d1b05ef760bf4d4733064ab3dad876e239b042e
|
| 3 |
size 21020682
|