mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
85dcfbef20
* 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]>
29 lines
722 B
Python
29 lines
722 B
Python
#!/usr/bin/env python
|
|
"""
|
|
Example of using SmolLM3 model with mistral.rs
|
|
"""
|
|
|
|
from mistralrs import Runner, Which, ChatCompletionRequest, Architecture
|
|
|
|
# Create a SmolLM3 model runner
|
|
runner = Runner(
|
|
which=Which.Plain(
|
|
model_id="HuggingFaceTB/SmolLM3-3B", # You can use any SmolLM3 model from HuggingFace
|
|
arch=Architecture.SmolLm3,
|
|
),
|
|
)
|
|
|
|
# Send a chat completion request
|
|
res = runner.send_chat_completion_request(
|
|
ChatCompletionRequest(
|
|
model="smollm3",
|
|
messages=[{"role": "user", "content": "What is the capital of France?"}],
|
|
max_tokens=256,
|
|
temperature=0.7,
|
|
)
|
|
)
|
|
|
|
# Print the response
|
|
print(res.choices[0].message.content)
|
|
print(f"\nUsage: {res.usage}")
|