Isabelle Cudlitz
commited on
Commit
·
8caaa55
1
Parent(s):
4147ec4
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4302,4 +4302,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4302 |
### Framework versions
|
| 4303 |
|
| 4304 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4305 |
- PEFT 0.6.2
|
|
|
|
| 4302 |
### Framework versions
|
| 4303 |
|
| 4304 |
|
| 4305 |
+
- PEFT 0.6.2
|
| 4306 |
+
## Training procedure
|
| 4307 |
+
|
| 4308 |
+
|
| 4309 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4310 |
+
- load_in_8bit: True
|
| 4311 |
+
- load_in_4bit: False
|
| 4312 |
+
- llm_int8_threshold: 6.0
|
| 4313 |
+
- llm_int8_skip_modules: None
|
| 4314 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4315 |
+
- llm_int8_has_fp16_weight: False
|
| 4316 |
+
- bnb_4bit_quant_type: fp4
|
| 4317 |
+
- bnb_4bit_use_double_quant: False
|
| 4318 |
+
- bnb_4bit_compute_dtype: float32
|
| 4319 |
+
|
| 4320 |
+
### Framework versions
|
| 4321 |
+
|
| 4322 |
+
|
| 4323 |
- 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 sha256:420189f211a8382b8a9fa27c578d789383efb322803809a7af151bd46c4d8f83
|
| 3 |
size 21020682
|