Isabelle Cudlitz
commited on
Commit
·
aa688cf
1
Parent(s):
03487d8
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2214,4 +2214,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2214 |
### Framework versions
|
| 2215 |
|
| 2216 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2217 |
- PEFT 0.6.2
|
|
|
|
| 2214 |
### Framework versions
|
| 2215 |
|
| 2216 |
|
| 2217 |
+
- PEFT 0.6.2
|
| 2218 |
+
## Training procedure
|
| 2219 |
+
|
| 2220 |
+
|
| 2221 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2222 |
+
- load_in_8bit: True
|
| 2223 |
+
- load_in_4bit: False
|
| 2224 |
+
- llm_int8_threshold: 6.0
|
| 2225 |
+
- llm_int8_skip_modules: None
|
| 2226 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2227 |
+
- llm_int8_has_fp16_weight: False
|
| 2228 |
+
- bnb_4bit_quant_type: fp4
|
| 2229 |
+
- bnb_4bit_use_double_quant: False
|
| 2230 |
+
- bnb_4bit_compute_dtype: float32
|
| 2231 |
+
|
| 2232 |
+
### Framework versions
|
| 2233 |
+
|
| 2234 |
+
|
| 2235 |
- 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:b24e155ba5474c9f005a82204faaa86de21ba334f5930333f4f4ebb7bf52672d
|
| 3 |
size 21020682
|