Isabelle Cudlitz
commited on
Commit
·
4147ec4
1
Parent(s):
6e49c18
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4284,4 +4284,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4284 |
### Framework versions
|
| 4285 |
|
| 4286 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4287 |
- PEFT 0.6.2
|
|
|
|
| 4284 |
### Framework versions
|
| 4285 |
|
| 4286 |
|
| 4287 |
+
- PEFT 0.6.2
|
| 4288 |
+
## Training procedure
|
| 4289 |
+
|
| 4290 |
+
|
| 4291 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4292 |
+
- load_in_8bit: True
|
| 4293 |
+
- load_in_4bit: False
|
| 4294 |
+
- llm_int8_threshold: 6.0
|
| 4295 |
+
- llm_int8_skip_modules: None
|
| 4296 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4297 |
+
- llm_int8_has_fp16_weight: False
|
| 4298 |
+
- bnb_4bit_quant_type: fp4
|
| 4299 |
+
- bnb_4bit_use_double_quant: False
|
| 4300 |
+
- bnb_4bit_compute_dtype: float32
|
| 4301 |
+
|
| 4302 |
+
### Framework versions
|
| 4303 |
+
|
| 4304 |
+
|
| 4305 |
- 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:bd88cbc5a26d08a330e2975236ef9d9055fd7916831e1e6ed0767cddfcda0fa7
|
| 3 |
size 21020682
|