From e075bd25ea45e92cf3b047fd3c18b6ad4bdc606e Mon Sep 17 00:00:00 2001
From: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
Date: Thu, 27 Jul 2023 15:30:56 -0400
Subject: [PATCH] chore: add NousResearch's as non-gated Llama (#152)

---
 .git-blame-ignore-revs                         |  1 +
 DEVELOPMENT.md                                 |  5 +++++
 README.md                                      | 18 ++++++++++++------
 .../models/llama/configuration_llama.py        | 18 ++++++++++++------
 4 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/.git-blame-ignore-revs b/.git-blame-ignore-revs
index e69de29b..f5aef396 100644
--- a/.git-blame-ignore-revs
+++ b/.git-blame-ignore-revs
@@ -0,0 +1 @@
+# You can use this file with 'git config blame.ignoreRevsFile .git-blame-ignore-revs'
diff --git a/DEVELOPMENT.md b/DEVELOPMENT.md
index da0de791..8b0630bb 100644
--- a/DEVELOPMENT.md
+++ b/DEVELOPMENT.md
@@ -153,6 +153,11 @@ To update the snapshot, do the following:
 hatch run tests:snapshot-models
 ```
 
+## Working with Git
+
+To filter out most of the generated commits for infrastructure, use ``--invert-grep`` in conjunction with ``--grep``
+to filter out all commits with regex `"[generated]"`
+
 ## Releasing a New Version
 
 To release a new version, use `./tools/run-release-action`. It requires `gh`,
diff --git a/README.md b/README.md
index 5b784cc0..a4d99649 100644
--- a/README.md
+++ b/README.md
@@ -254,12 +254,18 @@ pip install openllm
 <td><a href=https://huggingface.co/docs/transformers/main/model_doc/llama#transformers.LlamaForCausalLM><code>LlamaForCausalLM</code></a></td>
 <td>
 
-<ul><li><a href=https://huggingface.co/meta-llama/llama-2-70b-chat-hf><code>meta-llama/llama-2-70b-chat-hf</code></a></li>
-<li><a href=https://huggingface.co/meta-llama/llama-2-13b-chat-hf><code>meta-llama/llama-2-13b-chat-hf</code></a></li>
-<li><a href=https://huggingface.co/meta-llama/llama-2-7b-chat-hf><code>meta-llama/llama-2-7b-chat-hf</code></a></li>
-<li><a href=https://huggingface.co/meta-llama/llama-2-70b-hf><code>meta-llama/llama-2-70b-hf</code></a></li>
-<li><a href=https://huggingface.co/meta-llama/llama-2-13b-hf><code>meta-llama/llama-2-13b-hf</code></a></li>
-<li><a href=https://huggingface.co/meta-llama/llama-2-7b-hf><code>meta-llama/llama-2-7b-hf</code></a></li>
+<ul><li><a href=https://huggingface.co/meta-llama/Llama-2-70b-chat-hf><code>meta-llama/Llama-2-70b-chat-hf</code></a></li>
+<li><a href=https://huggingface.co/meta-llama/Llama-2-13b-chat-hf><code>meta-llama/Llama-2-13b-chat-hf</code></a></li>
+<li><a href=https://huggingface.co/meta-llama/Llama-2-7b-chat-hf><code>meta-llama/Llama-2-7b-chat-hf</code></a></li>
+<li><a href=https://huggingface.co/meta-llama/Llama-2-70b-hf><code>meta-llama/Llama-2-70b-hf</code></a></li>
+<li><a href=https://huggingface.co/meta-llama/Llama-2-13b-hf><code>meta-llama/Llama-2-13b-hf</code></a></li>
+<li><a href=https://huggingface.co/meta-llama/Llama-2-7b-hf><code>meta-llama/Llama-2-7b-hf</code></a></li>
+<li><a href=https://huggingface.co/NousResearch/llama-2-70b-chat-hf><code>NousResearch/llama-2-70b-chat-hf</code></a></li>
+<li><a href=https://huggingface.co/NousResearch/llama-2-13b-chat-hf><code>NousResearch/llama-2-13b-chat-hf</code></a></li>
+<li><a href=https://huggingface.co/NousResearch/llama-2-7b-chat-hf><code>NousResearch/llama-2-7b-chat-hf</code></a></li>
+<li><a href=https://huggingface.co/NousResearch/llama-2-70b-hf><code>NousResearch/llama-2-70b-hf</code></a></li>
+<li><a href=https://huggingface.co/NousResearch/llama-2-13b-hf><code>NousResearch/llama-2-13b-hf</code></a></li>
+<li><a href=https://huggingface.co/NousResearch/llama-2-7b-hf><code>NousResearch/llama-2-7b-hf</code></a></li>
 <li><a href=https://huggingface.co/openlm-research/open_llama_7b_v2><code>openlm-research/open_llama_7b_v2</code></a></li>
 <li><a href=https://huggingface.co/openlm-research/open_llama_3b_v2><code>openlm-research/open_llama_3b_v2</code></a></li>
 <li><a href=https://huggingface.co/openlm-research/open_llama_13b><code>openlm-research/open_llama_13b</code></a></li>
diff --git a/src/openllm/models/llama/configuration_llama.py b/src/openllm/models/llama/configuration_llama.py
index 856e7a98..fe2a3f03 100644
--- a/src/openllm/models/llama/configuration_llama.py
+++ b/src/openllm/models/llama/configuration_llama.py
@@ -36,12 +36,18 @@ class LlaMAConfig(openllm.LLMConfig):
         "architecture": "LlamaForCausalLM",
         "requirements": ["fairscale", "sentencepiece"],
         "model_ids": [
-            "meta-llama/llama-2-70b-chat-hf",
-            "meta-llama/llama-2-13b-chat-hf",
-            "meta-llama/llama-2-7b-chat-hf",
-            "meta-llama/llama-2-70b-hf",
-            "meta-llama/llama-2-13b-hf",
-            "meta-llama/llama-2-7b-hf",
+            "meta-llama/Llama-2-70b-chat-hf",
+            "meta-llama/Llama-2-13b-chat-hf",
+            "meta-llama/Llama-2-7b-chat-hf",
+            "meta-llama/Llama-2-70b-hf",
+            "meta-llama/Llama-2-13b-hf",
+            "meta-llama/Llama-2-7b-hf",
+            "NousResearch/llama-2-70b-chat-hf",
+            "NousResearch/llama-2-13b-chat-hf",
+            "NousResearch/llama-2-7b-chat-hf",
+            "NousResearch/llama-2-70b-hf",
+            "NousResearch/llama-2-13b-hf",
+            "NousResearch/llama-2-7b-hf",
             "openlm-research/open_llama_7b_v2",
             "openlm-research/open_llama_3b_v2",
             "openlm-research/open_llama_13b",