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]>
38 lines
1.0 KiB
Python
38 lines
1.0 KiB
Python
from mistralrs import Runner, Which, ChatCompletionRequest, VisionArchitecture
|
|
|
|
runner = Runner(
|
|
which=Which.VisionPlain(
|
|
model_id="HuggingFaceTB/SmolVLM-Instruct",
|
|
arch=VisionArchitecture.Idefics3,
|
|
),
|
|
)
|
|
|
|
res = runner.send_chat_completion_request(
|
|
ChatCompletionRequest(
|
|
model="default",
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "image_url",
|
|
"image_url": {
|
|
"url": "https://cdn.britannica.com/45/5645-050-B9EC0205/head-treasure-flower-disk-flowers-inflorescence-ray.jpg"
|
|
},
|
|
},
|
|
{
|
|
"type": "text",
|
|
"text": "What is shown in this image?",
|
|
},
|
|
],
|
|
},
|
|
],
|
|
max_tokens=256,
|
|
presence_penalty=1.0,
|
|
top_p=0.1,
|
|
temperature=0.1,
|
|
)
|
|
)
|
|
print(res.choices[0].message.content)
|
|
print(res.usage)
|