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]>
37 lines
841 B
Python
37 lines
841 B
Python
from mistralrs import (
|
|
Runner,
|
|
Which,
|
|
ChatCompletionRequest,
|
|
Architecture,
|
|
WebSearchOptions,
|
|
)
|
|
|
|
runner = Runner(
|
|
which=Which.Plain(
|
|
model_id="NousResearch/Hermes-3-Llama-3.1-8B",
|
|
arch=Architecture.Llama,
|
|
),
|
|
enable_search=True,
|
|
)
|
|
|
|
res = runner.send_chat_completion_request(
|
|
ChatCompletionRequest(
|
|
model="default",
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": "Can you show me some code using mistral.rs for running Llama 3.2 Vision?",
|
|
}
|
|
],
|
|
max_tokens=256,
|
|
presence_penalty=1.0,
|
|
top_p=0.1,
|
|
temperature=0.1,
|
|
web_search_options=WebSearchOptions(
|
|
search_context_size=None, user_location=None
|
|
),
|
|
)
|
|
)
|
|
print(res.choices[0].message.content)
|
|
print(res.usage)
|