mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
c3be7b6be4
* Add model * Update loader * Fix llama config usage * Docs * Fix config no_rope_layers * Fix tie_word_embeddings default * Add chat template * Embed the chat templates * Fix embedding template * enable_thinking default true * Update examples * XML tools for smollm3 * Add smollm3 docs * Fix openai examples * Clippy --------- Co-authored-by: Eric Buehler <[email protected]>
43 lines
1.0 KiB
Python
43 lines
1.0 KiB
Python
from mistralrs import Runner, Which, ChatCompletionRequest, Architecture
|
|
from json import dumps
|
|
|
|
runner = Runner(
|
|
which=Which.Plain(
|
|
model_id="microsoft/Phi-3.5-mini-instruct",
|
|
),
|
|
num_device_layers=["500"],
|
|
)
|
|
|
|
# see https://github.com/guidance-ai/llguidance/blob/main/docs/syntax.md for docs on syntax
|
|
|
|
top_lark = r"""
|
|
start: "Reasoning: " /.+/ "\nJSON: " answer
|
|
answer: %json {
|
|
"type": "object",
|
|
"properties": {
|
|
"answer": {"type": "string", "enum": ["Yes", "No"]}
|
|
},
|
|
"required": ["answer"],
|
|
"additionalProperties": false
|
|
}
|
|
"""
|
|
|
|
|
|
res = runner.send_chat_completion_request(
|
|
ChatCompletionRequest(
|
|
model="default",
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "If all dogs are mammals, and all mammals are animals, are dogs animals?",
|
|
}
|
|
],
|
|
max_tokens=100,
|
|
temperature=0.1,
|
|
grammar_type="lark",
|
|
grammar=top_lark,
|
|
)
|
|
)
|
|
print(res.choices[0].message.content)
|
|
print(res.usage)
|