phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 19:38:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-watsonx-inference-adapter

Browse source
This commit is contained in:
Sajikumar JS 2025-04-07 10:42:30 +05:30
commit 5366c423ae
10 changed files with 1355 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/models/llama/llama3/prompt_templates/system_prompts.py
View file

@ -279,6 +279,10 @@ class PythonListCustomToolGenerator(PromptTemplateGeneratorBase): # noqa: N801
{% endif -%}
{%- endfor %}
]
You can answer general questions or invoke tools when necessary.
In addition to tool calls, you should also augment your responses by using the tool outputs.
"""
)
return PromptTemplate(

5
llama_stack/models/llama/llama4/chat_format.py
View file

@ -216,9 +216,12 @@ class ChatFormat:
content = ToolUtils.encode_tool_call(t, tool_prompt_format)
_process_content(content)
# Tool calls and Tool Response messages should be eom
eom = False
if message.role == "assistant":
eom = message.stop_reason == StopReason.end_of_message
eom = message.stop_reason == StopReason.end_of_message or message.tool_calls
elif message.role == "tool":
eom = True
tokens.append(self.tokenizer.special_tokens["<|eom|>" if eom else "<|eot|>"])
return tokens, images