f64c3c8aba* Studio: add `unsloth chat` CLI command Interactive chat REPL on the shared Studio backend: trained-model picker when no model is given, /think and /compare toggles (adapter toggle on CUDA, side-by-side base-model load on MLX), markdown streaming, and connect-if-running Studio server mode so models stay warm across sessions and are shared with the UI. * fix settings * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix error handling and compare base precision * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix chat CLI backend imports and GGUF drafter loading * Hide split thinking tags in chat CLI streams --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Lee Jackson <130007945+Imagineer99@users.noreply.github.com> Co-authored-by: imagineer99 <samleejackson0@gmail.com>
76 lines
2.8 KiB
Python
76 lines
2.8 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
from typing import Optional
|
|
|
|
import typer
|
|
|
|
from unsloth_cli._inference import (
|
|
configure_quiet_logging,
|
|
connect_studio_server,
|
|
load_chat_backend,
|
|
stream_to_stdout,
|
|
)
|
|
|
|
|
|
def inference(
|
|
model: str = typer.Argument(..., help = "HF model id or local path."),
|
|
prompt: str = typer.Argument(..., help = "Prompt to send to the model."),
|
|
hf_token: Optional[str] = typer.Option(
|
|
None, "--hf-token", envvar = "HF_TOKEN", help = "Hugging Face token if needed."
|
|
),
|
|
temperature: float = typer.Option(0.7, "--temperature"),
|
|
top_p: float = typer.Option(0.9, "--top-p"),
|
|
top_k: int = typer.Option(40, "--top-k"),
|
|
max_new_tokens: int = typer.Option(256, "--max-new-tokens"),
|
|
repetition_penalty: float = typer.Option(1.1, "--repetition-penalty"),
|
|
system_prompt: str = typer.Option(
|
|
"",
|
|
"--system-prompt",
|
|
help = "Optional system prompt to prepend.",
|
|
),
|
|
max_seq_length: int = typer.Option(2048, "--max-seq-length"),
|
|
load_in_4bit: bool = typer.Option(True, "--load-in-4bit/--no-load-in-4bit"),
|
|
think: bool = typer.Option(
|
|
False,
|
|
"--think/--no-think",
|
|
help = "Show the model's <think> reasoning. Off by default so reasoning "
|
|
"models answer directly instead of spending the token budget thinking.",
|
|
),
|
|
verbose: bool = typer.Option(
|
|
False,
|
|
"--verbose",
|
|
"-v",
|
|
help = "Show backend and llama-server logs (otherwise only the answer).",
|
|
),
|
|
no_server: bool = typer.Option(
|
|
False,
|
|
"--no-server",
|
|
help = "Load the model in-process even if a Studio server is running.",
|
|
),
|
|
):
|
|
"""Run a single inference using the specified model."""
|
|
if not verbose:
|
|
configure_quiet_logging()
|
|
|
|
# A running Studio server keeps the model warm between runs, which is
|
|
# exactly what a one-shot command wants.
|
|
load_opts = dict(hf_token = hf_token, max_seq_length = max_seq_length, load_in_4bit = load_in_4bit)
|
|
chat_backend = None if no_server else connect_studio_server(model, **load_opts)
|
|
if chat_backend is None:
|
|
chat_backend = load_chat_backend(model, **load_opts)
|
|
try:
|
|
stream = chat_backend.stream(
|
|
[{"role": "user", "content": prompt}],
|
|
system_prompt = system_prompt,
|
|
temperature = temperature,
|
|
top_p = top_p,
|
|
top_k = top_k,
|
|
max_new_tokens = max_new_tokens,
|
|
repetition_penalty = repetition_penalty,
|
|
enable_thinking = think,
|
|
)
|
|
typer.echo("Assistant:")
|
|
stream_to_stdout(stream, show_thinking = think)
|
|
finally:
|
|
chat_backend.close()
|