Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +19 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- model_hub_mixin
|
| 5 |
+
- pytorch_model_hub_mixin
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 9 |
+
- Library: https://github.com/hieum98/lusifer
|
| 10 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_implementation": "flash_attention_2",
|
| 3 |
+
"connection_type": "ff",
|
| 4 |
+
"dropout": 0.1,
|
| 5 |
+
"encoder_backbone_type": "mistral",
|
| 6 |
+
"encoder_lora_name": "encoder_lora",
|
| 7 |
+
"encoder_lora_target_modules": "all",
|
| 8 |
+
"encoder_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 9 |
+
"is_freeze_encoder": true,
|
| 10 |
+
"is_freeze_universal_learner": false,
|
| 11 |
+
"loar_r": 16,
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"num_added_tokens": 0,
|
| 14 |
+
"pooling_method": "mean",
|
| 15 |
+
"universal_learner_backbone_type": "xlm-r",
|
| 16 |
+
"universal_learner_lora_name": "universal_learner_lora",
|
| 17 |
+
"universal_learner_lora_target_modules": "all",
|
| 18 |
+
"universal_learner_name_or_path": "Hieuman/xlm-aligned-for-mistral-v0.3"
|
| 19 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2be1f44140e55775179255cddebe99108e127752c4ceaba4966f2de6c8b8a0c6
|
| 3 |
+
size 15967515328
|