Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2250,4 +2250,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2250 |
### Framework versions
|
| 2251 |
|
| 2252 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2253 |
- PEFT 0.6.2
|
|
|
|
| 2250 |
### Framework versions
|
| 2251 |
|
| 2252 |
|
| 2253 |
+
- PEFT 0.6.2
|
| 2254 |
+
## Training procedure
|
| 2255 |
+
|
| 2256 |
+
|
| 2257 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2258 |
+
- load_in_8bit: True
|
| 2259 |
+
- load_in_4bit: False
|
| 2260 |
+
- llm_int8_threshold: 6.0
|
| 2261 |
+
- llm_int8_skip_modules: None
|
| 2262 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2263 |
+
- llm_int8_has_fp16_weight: False
|
| 2264 |
+
- bnb_4bit_quant_type: fp4
|
| 2265 |
+
- bnb_4bit_use_double_quant: False
|
| 2266 |
+
- bnb_4bit_compute_dtype: float32
|
| 2267 |
+
|
| 2268 |
+
### Framework versions
|
| 2269 |
+
|
| 2270 |
+
|
| 2271 |
- 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 sha256:3ffb9a54d198533ee66bb42fa4a6c3ebf5130dc1a73abda0b69752d2eed3668c
|
| 3 |
size 21020682
|