Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2340,4 +2340,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2340 |
### Framework versions
|
| 2341 |
|
| 2342 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2343 |
- PEFT 0.6.2
|
|
|
|
| 2340 |
### Framework versions
|
| 2341 |
|
| 2342 |
|
| 2343 |
+
- PEFT 0.6.2
|
| 2344 |
+
## Training procedure
|
| 2345 |
+
|
| 2346 |
+
|
| 2347 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2348 |
+
- load_in_8bit: True
|
| 2349 |
+
- load_in_4bit: False
|
| 2350 |
+
- llm_int8_threshold: 6.0
|
| 2351 |
+
- llm_int8_skip_modules: None
|
| 2352 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2353 |
+
- llm_int8_has_fp16_weight: False
|
| 2354 |
+
- bnb_4bit_quant_type: fp4
|
| 2355 |
+
- bnb_4bit_use_double_quant: False
|
| 2356 |
+
- bnb_4bit_compute_dtype: float32
|
| 2357 |
+
|
| 2358 |
+
### Framework versions
|
| 2359 |
+
|
| 2360 |
+
|
| 2361 |
- 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 sha256:7afe4da5c3a3071274a8a6ff4d76f3b4cc934e9258307bd04835955062d535d5
|
| 3 |
size 21020682
|