Isabelle Cudlitz
commited on
Commit
·
e526641
1
Parent(s):
b1aabc5
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1242,4 +1242,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1242 |
### Framework versions
|
| 1243 |
|
| 1244 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1245 |
- PEFT 0.6.2
|
|
|
|
| 1242 |
### Framework versions
|
| 1243 |
|
| 1244 |
|
| 1245 |
+
- PEFT 0.6.2
|
| 1246 |
+
## Training procedure
|
| 1247 |
+
|
| 1248 |
+
|
| 1249 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1250 |
+
- load_in_8bit: False
|
| 1251 |
+
- load_in_4bit: True
|
| 1252 |
+
- llm_int8_threshold: 6.0
|
| 1253 |
+
- llm_int8_skip_modules: None
|
| 1254 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1255 |
+
- llm_int8_has_fp16_weight: False
|
| 1256 |
+
- bnb_4bit_quant_type: fp4
|
| 1257 |
+
- bnb_4bit_use_double_quant: True
|
| 1258 |
+
- bnb_4bit_compute_dtype: float32
|
| 1259 |
+
|
| 1260 |
+
### Framework versions
|
| 1261 |
+
|
| 1262 |
+
|
| 1263 |
- 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:f6460e8a82b8b726a9aa06b06a9a3596684085a365a910fc5704e34c6194de03
|
| 3 |
size 21020682
|