วิธีรัน Underdog Saluki 27B: คู่มือ Tool-Calling ด้วยโมเดล 2-Bit

import os
import re
import ast
import sys
import json
import math
import copy
import enum
import glob
import time
import types
import random
import shutil
import struct
import hashlib
import tarfile
import platform
import traceback
import subprocess
import collections
import urllib.request
import urllib.error
 
RESULTS = {}
CLAIMS = []
CURRENT = ["1"]
 
def banner(title):
    print("\n" + "=" * 78)
    print(title)
    print("=" * 78)
 
def section(name):
    def wrap(fn):
        def run(*a, **kw):
            CURRENT[0] = name.split(".")[0]
            banner(name)
            t0 = time.time()
            try:
                out = fn(*a, **kw)
                RESULTS[name] = out if isinstance(out, str) else "ok"
                return out
            except Exception as e:
                RESULTS[name] = f"SKIPPED / FAILED -> {type(e).__name__}: {e}"
                print(f"\n[!] {name} did not complete: {type(e).__name__}: {e}")
                traceback.print_exc(limit=3)
                return None
            finally:
                print(f"\n[{time.time() - t0:.1f} s]")
                json.dump({"results": RESULTS, "claims": CLAIMS}, open(os.path.join(WORK, "results.json"), "w"), indent=1)
        return run
    return wrap
 
def claim(text, held):
    CLAIMS.append((CURRENT[0], text, held))
    return held
 
banner("1. Platform, pins and helpers")
SYSTEM, MACHINE = platform.system(), platform.machine()
ON_CUDA = SYSTEM == "Linux" and shutil.which("nvidia-smi") is not None
assert ON_CUDA or (SYSTEM == "Darwin" and MACHINE == "arm64"), "needs an NVIDIA GPU on Linux (Colab T4) or an Apple-silicon Mac"
WORK = os.environ.get("SALUKI_WORK") or ("/content/saluki" if os.path.isdir("/content") else os.path.abspath("saluki_work"))
for d in ("models", "llama", "bfcl", "runs"):
    os.makedirs(os.path.join(WORK, d), exist_ok=True)
 
LLAMA_TAG = "b11565"
LLAMA_ASSET = {"Linux": ("llama-b11565-bin-ubuntu-cuda-12.8-x64.tar.gz", 171559844,
                         "61b8cf4e49739afe4008b06a92390dff999e706e9e7e9749c015544a9f241627"),
               "Darwin": ("llama-b11565-bin-macos-arm64.tar.gz", 12105509,
                          "19289548468babcd5131cecccf3a9bc7c67030cc7f0a978dafc0db1ba7891068")}[SYSTEM]
MODELS = {
    "Saluki": dict(repo="ConwayResearch/Underdog-Saluki-27B-1.0", rev="4f60eba09f4b6db63c72915d328d97e1d93edb8c",
                   file="Underdog-Saluki-27B-1.0-IQ2-mix.gguf", size=7898369152,
                   sha256="4a673518b11b1c4445f9b9a9d3c40356f5ba39f6a6260dcb25f3fbfd475d9efb"),
    "ISTA": dict(repo="ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF", rev="d562806dbafae37109975e970aae91b43e73b440",
                 file="Qwen3.8-27B-GSQ-RCO-IQ2_XS.gguf", size=8422841472,
                 sha256="f0ae5006da0ce6225935339e4e989369f94de95d2263cf969519f8420c9ae02c"),
}
GORILLA = ("https://raw.githubusercontent.com/ShishirPatil/gorilla/6ea57973c7a6097fd7c5915698c54c17c5b1b6c8/"
           "berkeley-function-call-leaderboard/bfcl_eval/")
BFCL_FILES = {
    "data/BFCL_v4_simple_python.json": "82dd63ba502eb2520c6b5d1d9a5c4b590e03ff261565175561f6228a367d1991",
    "data/BFCL_v4_multiple.json": "aef168155ebd74b7ac2401198b201343bc7d16d7a3d7e0d4e6d8ee82c6969b2a",
    "data/BFCL_v4_irrelevance.json": "2b6ed4c2e992cdcf5f1678a701851f944bef7550ee026ed1ddb89efed5be01a6",
    "data/BFCL_v4_parallel.json": "19f51a82eff42e5d62541aa500115a056eb78f437c2ba1f10415fd7c8e5dda84",
    "data/BFCL_v4_parallel_multiple.json": "8863ea8433239f55c5f016154cf0830853c89f693c6ea270396a2fa121960579",
    "data/possible_answer/BFCL_v4_simple_python.json": "90cd5bc653690ee8e459b5b3f3fc9458606f7f3fcbf795bb51b7dc581f8c86dc",
    "data/possible_answer/BFCL_v4_multiple.json": "244e00ce9395df948bcafc7bee64e8f9c87ef70887587d83cae45b13699f3047",
    "data/possible_answer/BFCL_v4_parallel.json": "8a6aa19c1adddc6a5a2f7e40f9dbf30cc7e95815e7b830c90589ab318229e0f0",
    "data/possible_answer/BFCL_v4_parallel_multiple.json": "5ebf24f458c1f16300c05505d83d6f0a1b68b79be273a033febd0d4f840507e3",
    "eval_checker/ast_eval/ast_checker.py": "2aae7a68461a8f76c0be3894c8901b66b56967a1989d3ab066051e3fb97f1538",
    "constants/enums.py": "2182becfa2a1d071ee1db30db593b4758c6bf866aa12d2d4b8daf09175ea518a",
    "constants/type_mappings.py": "1702fb67afbe2c492608e58e2b7d02e46381f50166b47f3c952f76e34c7cd3bd",
    "utils.py": "3703b9bb63f83581c60b8e0b82aac74c360c9ca781e99e7d4eb28b0cce2285dd",
    "model_handler/utils.py": "f78fd3edce603b333dc9a88ee2c041dc547d51f71aa449ffebc044c4b1e353f3",
}
KINDS = [("simple_python", "Call the one right function"), ("multiple", "Pick the right function from several"),
         ("irrelevance", "Know when no tool fits"), ("parallel", "Same function, several calls"),
         ("parallel_multiple", "Several different functions")]
N_PER_KIND, SEED, CTX, PORT = 24, 2026, 16384, 8080
GREEDY = dict(temperature=0, top_k=0, top_p=1.0, min_p=0)
 
def sh(cmd, **kw):
    return subprocess.run(cmd, capture_output=True, text=True, **kw)
 
def sha256_file(path, chunk=1 << 22):
    h = hashlib.sha256()
    with open(path, "rb") as f:
        for b in iter(lambda: f.read(chunk), b""):
            h.update(b)
    return h.hexdigest()
 
def fetch(url, dest, size=None, sha=None, quiet=False):
    t0 = time.time()
    if not (os.path.exists(dest) and (size is None or os.path.getsize(dest) == size)):
        for attempt in range(5):
            r = sh(["curl", "-fsSL", "-C", "-", "--retry", "5", "-o", dest, url])
            if r.returncode == 0 and (size is None or os.path.getsize(dest) == size):
                break
            time.sleep(5 * (attempt + 1))
    got = os.path.getsize(dest)
    assert size is None or got == size, f"{os.path.basename(dest)}: {got} bytes, expected {size}"
    if sha:
        assert sha256_file(dest) == sha, f"{os.path.basename(dest)}: SHA-256 mismatch"
    return time.time() - t0
 
print(f"platform : {SYSTEM} {MACHINE}, Python {platform.python_version()}, glibc {platform.libc_ver()[1] or 'n/a'}")
if SYSTEM == "Linux":
    print("os       :", open("/etc/os-release").read().split('PRETTY_NAME="')[1].split('"')[0])
    gpu = sh(["nvidia-smi", "--query-gpu=name,memory.total,driver_version", "--format=csv,noheader"]).stdout.strip()
    print("gpu      :", gpu)
    import importlib.util
    if importlib.util.find_spec("nvidia.cuda_runtime") is None or importlib.util.find_spec("nvidia.cublas") is None:
        subprocess.run([sys.executable, "-m", "pip", "install", "-q", "nvidia-cuda-runtime-cu12==12.9.79",
                        "nvidia-cublas-cu12==12.9.2.10"], check=True)
    import nvidia.cuda_runtime, nvidia.cublas
    CUDA_LIBS = [os.path.join(list(m.__path__)[0], "lib") for m in (nvidia.cuda_runtime, nvidia.cublas)]
else:
    chip = sh(["sysctl", "-n", "machdep.cpu.brand_string"]).stdout.strip()
    mem = int(sh(["sysctl", "-n", "hw.memsize"]).stdout) / 2**30
    print(f"gpu      : {chip}, {mem:.0f} GB unified memory (Metal)")
    CUDA_LIBS = []
HW = gpu.split(",")[0] if SYSTEM == "Linux" else chip
print(f"work dir : {WORK}  ({shutil.disk_usage(WORK).free / 1e9:.0f} GB free)")