Upload model
Browse files- README.md +12 -0
- adapter_config.json +2 -2
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -201,6 +201,18 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 201 |
## Training procedure
|
| 202 |
|
| 203 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
### Framework versions
|
| 205 |
|
| 206 |
|
|
|
|
| 201 |
## Training procedure
|
| 202 |
|
| 203 |
|
| 204 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
+
- quant_method: bitsandbytes
|
| 206 |
+
- load_in_8bit: True
|
| 207 |
+
- load_in_4bit: False
|
| 208 |
+
- llm_int8_threshold: 6.0
|
| 209 |
+
- llm_int8_skip_modules: None
|
| 210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
+
- llm_int8_has_fp16_weight: False
|
| 212 |
+
- bnb_4bit_quant_type: fp4
|
| 213 |
+
- bnb_4bit_use_double_quant: False
|
| 214 |
+
- bnb_4bit_compute_dtype: float32
|
| 215 |
+
|
| 216 |
### Framework versions
|
| 217 |
|
| 218 |
|
adapter_config.json
CHANGED
|
@@ -16,8 +16,8 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
],
|
| 22 |
"task_type": "SEQ_2_SEQ_LM"
|
| 23 |
}
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
+
"v",
|
| 20 |
+
"q"
|
| 21 |
],
|
| 22 |
"task_type": "SEQ_2_SEQ_LM"
|
| 23 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18980429
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c40863f6e0cc7bb9332f9f5b7b5a4e03855c436f9d44061c98c0e4a5b0270226
|
| 3 |
size 18980429
|