Llama3.2 vision model support (#1551)

This commit is contained in:
Liangsheng Yin
2024-10-21 15:01:21 -07:00
committed by GitHub
parent 00611286a1
commit 94cde10920
21 changed files with 1562 additions and 122 deletions
+13
View File
@@ -509,6 +509,19 @@ register_conv_template(
)
)
register_conv_template(
Conversation(
name="llama_3_vision",
system_message="You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.",
system_template="<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>",
roles=("user", "assistant"),
sep_style=SeparatorStyle.LLAMA3,
sep="",
stop_str=["<|end_of_text|>", "<|eot_id|>"],
image_token="<|image|>",
)
)
register_conv_template(
Conversation(
name="llava_llama_3",