Isabelle Cudlitz
commited on
Commit
·
7a508ab
1
Parent(s):
aa688cf
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2232,4 +2232,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2232 |
### Framework versions
|
| 2233 |
|
| 2234 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2235 |
- PEFT 0.6.2
|
|
|
|
| 2232 |
### Framework versions
|
| 2233 |
|
| 2234 |
|
| 2235 |
+
- PEFT 0.6.2
|
| 2236 |
+
## Training procedure
|
| 2237 |
+
|
| 2238 |
+
|
| 2239 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2240 |
+
- load_in_8bit: True
|
| 2241 |
+
- load_in_4bit: False
|
| 2242 |
+
- llm_int8_threshold: 6.0
|
| 2243 |
+
- llm_int8_skip_modules: None
|
| 2244 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2245 |
+
- llm_int8_has_fp16_weight: False
|
| 2246 |
+
- bnb_4bit_quant_type: fp4
|
| 2247 |
+
- bnb_4bit_use_double_quant: False
|
| 2248 |
+
- bnb_4bit_compute_dtype: float32
|
| 2249 |
+
|
| 2250 |
+
### Framework versions
|
| 2251 |
+
|
| 2252 |
+
|
| 2253 |
- 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:a2fddecd7b180a6a97c791ae86b17484d8433827f833ea87f222656e143b27d4
|
| 3 |
size 21020682
|