adding llama3 fastchat conversation monkeypatch (#1539)

* adding llama3 fastchat conversation monkeypatch * Updated conversation turns to work with PR3259 of FastChat * fixed bos token * bump fastchat version --------- Co-authored-by: Wing Lian <[email protected]>
axolotl-ai-cloud · May 10, 2024 · b32c08f · b32c08f
1 parent fff06af
commit b32c08f
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 1 deletion.
diff --git a/requirements.txt b/requirements.txt
@@ -28,7 +28,7 @@ scipy
 scikit-learn==1.2.2
 pynvml
 art
-fschat @ git+https://github.com/lm-sys/FastChat.git@5095615810cf613dba7f27dd155f571fcff976d8
+fschat @ git+https://github.com/lm-sys/FastChat.git@27a05b04a35510afb1d767ae7e5990cbd278f8fe
 gradio==3.50.2
 tensorboard
 

diff --git a/src/axolotl/monkeypatch/fastchat_conversation_turns.py b/src/axolotl/monkeypatch/fastchat_conversation_turns.py
@@ -123,6 +123,17 @@ def get_turns(  # pylint: disable=too-many-return-statements
             else:
                 yield role, ""
         return
+    if self.sep_style == SeparatorStyle.LLAMA3:
+        if self.system_message:
+            # For llama3, the system message is NOT incorporated into the first human instruction
+            # All messages follow <|start_header_id|>' + role + '<|end_header_id|>\n\n'+ message + '<|eot_id|>
+            yield "", system_prompt
+        for i, (role, message) in enumerate(self.messages):
+            if message:
+                yield f"<|start_header_id|>{role}<|end_header_id|>\n\n", f"{message.strip()}<|eot_id|>"
+            else:
+                yield f"<|start_header_id|>{role}<|end_header_id|>\n\n", ""
+        return
     if self.sep_style == SeparatorStyle.GEMMA:
         if self.system_message:
             raise ValueError("Gemma chat template does not support system messages")