Isabelle Cudlitz
commited on
Commit
·
5bd792a
1
Parent(s):
b7d4afb
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2304,4 +2304,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2304 |
### Framework versions
|
| 2305 |
|
| 2306 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2307 |
- PEFT 0.6.2
|
|
|
|
| 2304 |
### Framework versions
|
| 2305 |
|
| 2306 |
|
| 2307 |
+
- PEFT 0.6.2
|
| 2308 |
+
## Training procedure
|
| 2309 |
+
|
| 2310 |
+
|
| 2311 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2312 |
+
- load_in_8bit: True
|
| 2313 |
+
- load_in_4bit: False
|
| 2314 |
+
- llm_int8_threshold: 6.0
|
| 2315 |
+
- llm_int8_skip_modules: None
|
| 2316 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2317 |
+
- llm_int8_has_fp16_weight: False
|
| 2318 |
+
- bnb_4bit_quant_type: fp4
|
| 2319 |
+
- bnb_4bit_use_double_quant: False
|
| 2320 |
+
- bnb_4bit_compute_dtype: float32
|
| 2321 |
+
|
| 2322 |
+
### Framework versions
|
| 2323 |
+
|
| 2324 |
+
|
| 2325 |
- 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 sha256:3da539af7fb908ad08352c775eeb2ad3c204bc2c198442844be7f384daa7dc13
|
| 3 |
size 21020682
|