Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2322,4 +2322,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2322 |
### Framework versions
|
| 2323 |
|
| 2324 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2325 |
- PEFT 0.6.2
|
|
|
|
| 2322 |
### Framework versions
|
| 2323 |
|
| 2324 |
|
| 2325 |
+
- PEFT 0.6.2
|
| 2326 |
+
## Training procedure
|
| 2327 |
+
|
| 2328 |
+
|
| 2329 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2330 |
+
- load_in_8bit: True
|
| 2331 |
+
- load_in_4bit: False
|
| 2332 |
+
- llm_int8_threshold: 6.0
|
| 2333 |
+
- llm_int8_skip_modules: None
|
| 2334 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2335 |
+
- llm_int8_has_fp16_weight: False
|
| 2336 |
+
- bnb_4bit_quant_type: fp4
|
| 2337 |
+
- bnb_4bit_use_double_quant: False
|
| 2338 |
+
- bnb_4bit_compute_dtype: float32
|
| 2339 |
+
|
| 2340 |
+
### Framework versions
|
| 2341 |
+
|
| 2342 |
+
|
| 2343 |
- 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:c871ecf804b0098ab68e851b9555ba763bb7e32d112186c17d224e06698c7646
|
| 3 |
size 21020682
|