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]>
28 lines
799 B
Python
28 lines
799 B
Python
from mistralrs import Runner, Which, ChatCompletionRequest
|
|
|
|
runner = Runner(
|
|
which=Which.LoraGGUF(
|
|
tok_model_id=None, # Automatically determine from ordering file
|
|
quantized_model_id="TheBloke/zephyr-7B-beta-GGUF",
|
|
quantized_filename="zephyr-7b-beta.Q4_0.gguf",
|
|
xlora_model_id="lamm-mit/x-lora",
|
|
order="orderings/xlora-paper-ordering.json",
|
|
)
|
|
)
|
|
|
|
res = runner.send_chat_completion_request(
|
|
ChatCompletionRequest(
|
|
model="default",
|
|
messages=[
|
|
{"role": "user", "content": "Tell me a story about the Rust type system."}
|
|
],
|
|
max_tokens=256,
|
|
presence_penalty=1.0,
|
|
top_p=0.1,
|
|
temperature=0.5,
|
|
adapters=["adapter_4"],
|
|
)
|
|
)
|
|
print(res.choices[0].message.content)
|
|
print(res.usage)
|