From 22f71c152ac3b8e92cfa3530d4727b3d25298cf8 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Fri, 17 May 2024 00:08:33 +0800
Subject: [PATCH] add falcon 11b

Former-commit-id: d77bed4091a6a8fea682b39d3261e1e93dfe093f
---
 README.md                            | 2 +-
 README_zh.md                         | 2 +-
 src/llamafactory/extras/constants.py | 3 +++
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index d392b19b..a41415fd 100644
--- a/README.md
+++ b/README.md
@@ -149,7 +149,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 | [ChatGLM3](https://huggingface.co/THUDM)                 | 6B                               | query_key_value   | chatglm3  |
 | [Command-R](https://huggingface.co/CohereForAI)          | 35B/104B                         | q_proj,v_proj     | cohere    |
 | [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | q_proj,v_proj     | deepseek  |
-| [Falcon](https://huggingface.co/tiiuae)                  | 7B/40B/180B                      | query_key_value   | falcon    |
+| [Falcon](https://huggingface.co/tiiuae)                  | 7B/11B/40B/180B                  | query_key_value   | falcon    |
 | [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                            | q_proj,v_proj     | gemma     |
 | [InternLM2](https://huggingface.co/internlm)             | 7B/20B                           | wqkv              | intern2   |
 | [LLaMA](https://github.com/facebookresearch/llama)       | 7B/13B/33B/65B                   | q_proj,v_proj     | -         |
diff --git a/README_zh.md b/README_zh.md
index 58398a31..4f8ffa28 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -149,7 +149,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 | [ChatGLM3](https://huggingface.co/THUDM)                 | 6B                               | query_key_value   | chatglm3  |
 | [Command-R](https://huggingface.co/CohereForAI)          | 35B/104B                         | q_proj,v_proj     | cohere    |
 | [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | q_proj,v_proj     | deepseek  |
-| [Falcon](https://huggingface.co/tiiuae)                  | 7B/40B/180B                      | query_key_value   | falcon    |
+| [Falcon](https://huggingface.co/tiiuae)                  | 7B/11B/40B/180B                  | query_key_value   | falcon    |
 | [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                            | q_proj,v_proj     | gemma     |
 | [InternLM2](https://huggingface.co/internlm)             | 7B/20B                           | wqkv              | intern2   |
 | [LLaMA](https://github.com/facebookresearch/llama)       | 7B/13B/33B/65B                   | q_proj,v_proj     | -         |
diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py
index f1ee55a0..40826163 100644
--- a/src/llamafactory/extras/constants.py
+++ b/src/llamafactory/extras/constants.py
@@ -375,6 +375,9 @@ register_model_group(
             DownloadSource.DEFAULT: "tiiuae/falcon-7b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/falcon-7b",
         },
+        "Falcon-11B": {
+            DownloadSource.DEFAULT: "tiiuae/falcon-11B",
+        },
         "Falcon-40B": {
             DownloadSource.DEFAULT: "tiiuae/falcon-40b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/falcon-40b",