Isabelle Cudlitz
commited on
Commit
·
c9777dd
1
Parent(s):
8caaa55
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4320,4 +4320,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4320 |
### Framework versions
|
| 4321 |
|
| 4322 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4323 |
- PEFT 0.6.2
|
|
|
|
| 4320 |
### Framework versions
|
| 4321 |
|
| 4322 |
|
| 4323 |
+
- PEFT 0.6.2
|
| 4324 |
+
## Training procedure
|
| 4325 |
+
|
| 4326 |
+
|
| 4327 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4328 |
+
- load_in_8bit: True
|
| 4329 |
+
- load_in_4bit: False
|
| 4330 |
+
- llm_int8_threshold: 6.0
|
| 4331 |
+
- llm_int8_skip_modules: None
|
| 4332 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4333 |
+
- llm_int8_has_fp16_weight: False
|
| 4334 |
+
- bnb_4bit_quant_type: fp4
|
| 4335 |
+
- bnb_4bit_use_double_quant: False
|
| 4336 |
+
- bnb_4bit_compute_dtype: float32
|
| 4337 |
+
|
| 4338 |
+
### Framework versions
|
| 4339 |
+
|
| 4340 |
+
|
| 4341 |
- 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 sha256:4a409f29badff67d2913f5d575af5f0697d62c22ab8c25c202b1c1260ad106a9
|
| 3 |
size 21020682
|