basic training
Browse files- README.md +0 -11
- adapter_config.json +1 -1
- adapter_model.bin +2 -2
README.md
CHANGED
|
@@ -201,17 +201,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 201 |
## Training procedure
|
| 202 |
|
| 203 |
|
| 204 |
-
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
-
- load_in_8bit: True
|
| 206 |
-
- load_in_4bit: False
|
| 207 |
-
- llm_int8_threshold: 6.0
|
| 208 |
-
- llm_int8_skip_modules: None
|
| 209 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
| 210 |
-
- llm_int8_has_fp16_weight: False
|
| 211 |
-
- bnb_4bit_quant_type: fp4
|
| 212 |
-
- bnb_4bit_use_double_quant: False
|
| 213 |
-
- bnb_4bit_compute_dtype: float32
|
| 214 |
-
|
| 215 |
### Framework versions
|
| 216 |
|
| 217 |
|
|
|
|
| 201 |
## Training procedure
|
| 202 |
|
| 203 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
### Framework versions
|
| 205 |
|
| 206 |
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path":
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bigscience/bloom-560m",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57b83ba451ba2cbde2097319bfcd221c2245fbe77930b6a406e8a1ea7b85e655
|
| 3 |
+
size 6309630
|