Upload model

README.md

@@ -0,0 +1,42 @@
+---
+tags:
+- llama
+- adapter-transformers
+datasets:
+- mrpc
+---
+
+# Adapter `freakreation/my_adapterfusion_adapters` for ../models/llama-3.2-1b/llama-3.2-1b-model
+
+An [adapter](https://adapterhub.ml) for the `../models/llama-3.2-1b/llama-3.2-1b-model` model that was trained on the [mrpc](https://huggingface.co/datasets/mrpc/) dataset and includes a prediction head for classification.
+
+This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
+
+## Usage
+
+First, install `adapters`:
+
+```
+pip install -U adapters
+```
+
+Now, the adapter can be loaded and activated like this:
+
+```python
+from adapters import AutoAdapterModel
+
+model = AutoAdapterModel.from_pretrained("../models/llama-3.2-1b/llama-3.2-1b-model")
+adapter_name = model.load_adapter("freakreation/my_adapterfusion_adapters", set_active=True)
+```
+
+## Architecture & Training
+
+<!-- Add some description here -->
+
+## Evaluation results
+
+<!-- Add some description here -->
+
+## Citation
+
+<!-- Add some description here -->

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "stochastic_depth": 0.0,
+    "use_gating": false
+  },
+  "hidden_size": 2048,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "../models/llama-3.2-1b/llama-3.2-1b-model",
+  "model_type": "llama",
+  "name": "mrpc_seq_bn_upload",
+  "version": "adapters.1.1.0"
+}

head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 2048,
+  "model_class": "LlamaAdapterModel",
+  "model_name": "../models/llama-3.2-1b/llama-3.2-1b-model",
+  "model_type": "llama",
+  "name": "mrpc_seq_bn_upload",
+  "version": "adapters.1.1.0"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92db96a25af62b5ab052674c51bb98fc59f645903df74fefcbe1d120e11e6372
+size 33716982

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a235ff58288e245e8a3ae823813edda4502264d7d9542d1f6669787cc0d4f9
+size 16803944