Upload LlamaForCausalLM

README.md

@@ -0,0 +1,42 @@
+---
+tags:
+- adapter-transformers
+- llama
+datasets:
+- timdettmers/openassistant-guanaco
+---
+
+# Adapter `AdapterHub/llama2-7b-qadapter-seq-openassistant` for meta-llama/Llama-2-7b-hf
+
+An [adapter](https://adapterhub.ml) for the `meta-llama/Llama-2-7b-hf` model that was trained on the [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco/) dataset.
+
+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("meta-llama/Llama-2-7b-hf")
+adapter_name = model.load_adapter("AdapterHub/llama2-7b-qadapter-seq-openassistant", source="hf", 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 +1,41 @@
+{
+  "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": true,
+    "non_linearity": "swish",
+    "original_ln_after": true,
+    "original_ln_before": false,
+    "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,
+    "use_gating": false
+  },
+  "hidden_size": 4096,
+  "model_class": "LlamaForCausalLM",
+  "model_name": "meta-llama/Llama-2-7b-hf",
+  "model_type": "llama",
+  "name": "assistant_adapter",
+  "version": "0.1.2"
+}

head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "LlamaForCausalLM",
+  "model_name": "meta-llama/Llama-2-7b-hf",
+  "model_type": "llama",
+  "name": null,
+  "num_labels": 2,
+  "version": "0.1.2"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed43c49e184c09bbed3c779eebc754ba2921a914249f5ff45f4178fc537dae8
+size 538078290

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9ee5a61b2365fec20b5e7b3a2cace257479506d2662810467066df826f2a02
+size 262145299