Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2286,4 +2286,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2286 |
### Framework versions
|
| 2287 |
|
| 2288 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2289 |
- PEFT 0.6.2
|
|
|
|
| 2286 |
### Framework versions
|
| 2287 |
|
| 2288 |
|
| 2289 |
+
- PEFT 0.6.2
|
| 2290 |
+
## Training procedure
|
| 2291 |
+
|
| 2292 |
+
|
| 2293 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2294 |
+
- load_in_8bit: True
|
| 2295 |
+
- load_in_4bit: False
|
| 2296 |
+
- llm_int8_threshold: 6.0
|
| 2297 |
+
- llm_int8_skip_modules: None
|
| 2298 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2299 |
+
- llm_int8_has_fp16_weight: False
|
| 2300 |
+
- bnb_4bit_quant_type: fp4
|
| 2301 |
+
- bnb_4bit_use_double_quant: False
|
| 2302 |
+
- bnb_4bit_compute_dtype: float32
|
| 2303 |
+
|
| 2304 |
+
### Framework versions
|
| 2305 |
+
|
| 2306 |
+
|
| 2307 |
- 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 sha256:6d1e2c9f39e087b4fcb5484eed65a1347123d145567f35bd1339ceea5ffa5475
|
| 3 |
size 21020682
|