Text Generation
Adapters
llama
llama-2
calpt commited on
Commit
65505ef
1 Parent(s): 91f152c

Upload LlamaForCausalLM

Browse files
README.md ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - adapter-transformers
4
+ - llama
5
+ datasets:
6
+ - timdettmers/openassistant-guanaco
7
+ ---
8
+
9
+ # Adapter `AdapterHub/llama2-7b-qadapter-seq-openassistant` for meta-llama/Llama-2-7b-hf
10
+
11
+ 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.
12
+
13
+ This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
14
+
15
+ ## Usage
16
+
17
+ First, install `adapters`:
18
+
19
+ ```
20
+ pip install -U adapters
21
+ ```
22
+
23
+ Now, the adapter can be loaded and activated like this:
24
+
25
+ ```python
26
+ from adapters import AutoAdapterModel
27
+
28
+ model = AutoAdapterModel.from_pretrained("meta-llama/Llama-2-7b-hf")
29
+ adapter_name = model.load_adapter("AdapterHub/llama2-7b-qadapter-seq-openassistant", source="hf", set_active=True)
30
+ ```
31
+
32
+ ## Architecture & Training
33
+
34
+ <!-- Add some description here -->
35
+
36
+ ## Evaluation results
37
+
38
+ <!-- Add some description here -->
39
+
40
+ ## Citation
41
+
42
+ <!-- Add some description here -->
adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "dropout": 0.0,
6
+ "factorized_phm_W": true,
7
+ "factorized_phm_rule": false,
8
+ "hypercomplex_nonlinearity": "glorot-uniform",
9
+ "init_weights": "bert",
10
+ "inv_adapter": null,
11
+ "inv_adapter_reduction_factor": null,
12
+ "is_parallel": false,
13
+ "learn_phm": true,
14
+ "leave_out": [],
15
+ "ln_after": false,
16
+ "ln_before": false,
17
+ "mh_adapter": true,
18
+ "non_linearity": "swish",
19
+ "original_ln_after": true,
20
+ "original_ln_before": false,
21
+ "output_adapter": true,
22
+ "phm_bias": true,
23
+ "phm_c_init": "normal",
24
+ "phm_dim": 4,
25
+ "phm_init_range": 0.0001,
26
+ "phm_layer": false,
27
+ "phm_rank": 1,
28
+ "reduction_factor": 16,
29
+ "residual_before_ln": true,
30
+ "scaling": 1.0,
31
+ "shared_W_phm": false,
32
+ "shared_phm_rule": true,
33
+ "use_gating": false
34
+ },
35
+ "hidden_size": 4096,
36
+ "model_class": "LlamaForCausalLM",
37
+ "model_name": "meta-llama/Llama-2-7b-hf",
38
+ "model_type": "llama",
39
+ "name": "assistant_adapter",
40
+ "version": "0.1.2"
41
+ }
head_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 4096,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1
7
+ },
8
+ "model_class": "LlamaForCausalLM",
9
+ "model_name": "meta-llama/Llama-2-7b-hf",
10
+ "model_type": "llama",
11
+ "name": null,
12
+ "num_labels": 2,
13
+ "version": "0.1.2"
14
+ }
pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed43c49e184c09bbed3c779eebc754ba2921a914249f5ff45f4178fc537dae8
3
+ size 538078290
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9ee5a61b2365fec20b5e7b3a2cace257479506d2662810467066df826f2a02
3
+ size 262145299