quantprobe 1.5.0__tar.gz → 1.5.1__tar.gz

{quantprobe-1.5.0/quantprobe.egg-info → quantprobe-1.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantprobe
-Version: 1.5.0
+Version: 1.5.1
 Summary: Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes.
 Author: Federico Sciuca
 License: MIT
@@ -96,6 +96,7 @@ quantprobe auto qwen3-coder --tps 15 --run   # empty machine -> optimal quant ch
 
 ```bash
 quantprobe auto qwen3-30b --tps 15                       # ONE command: optimizer picks bits, closest quant fetched, run command printed
+quantprobe auto qwen3-30b --custom                       # THE PRODUCT: probe YOUR model, build its personalized depth-aware GGUF
 quantprobe hw                                            # what the law sees on THIS machine (every value source-tagged)
 quantprobe plan     --gguf model.gguf                    # zero-config prediction: placement + tok/s + the launch command
 quantprobe optimize --tps 20                             # CHEAPEST PATH to a target: bits x placement x hardware, Pareto-ranked

{quantprobe-1.5.0 → quantprobe-1.5.1}/README.md

@@ -78,6 +78,7 @@ quantprobe auto qwen3-coder --tps 15 --run   # empty machine -> optimal quant ch
 
 ```bash
 quantprobe auto qwen3-30b --tps 15                       # ONE command: optimizer picks bits, closest quant fetched, run command printed
+quantprobe auto qwen3-30b --custom                       # THE PRODUCT: probe YOUR model, build its personalized depth-aware GGUF
 quantprobe hw                                            # what the law sees on THIS machine (every value source-tagged)
 quantprobe plan     --gguf model.gguf                    # zero-config prediction: placement + tok/s + the launch command
 quantprobe optimize --tps 20                             # CHEAPEST PATH to a target: bits x placement x hardware, Pareto-ranked

{quantprobe-1.5.0 → quantprobe-1.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "quantprobe"
-version = "1.5.0"
+version = "1.5.1"
 description = "Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes."
 readme = "README.md"
 license = { text = "MIT" }

{quantprobe-1.5.0 → quantprobe-1.5.1}/quantprobe/__init__.py

@@ -8,4 +8,4 @@ Three commands, all grounded in measured laws (see LAWS.md in the repo):
 Every constant in `plan` is fitted from measurements published in the repo, including two
 pre-registered hardware predictions confirmed within 8%.
 """
-__version__ = "1.5.0"
+__version__ = "1.5.1"

{quantprobe-1.5.0 → quantprobe-1.5.1}/quantprobe/auto.py

@@ -37,6 +37,37 @@ def list_ggufs(repo):
                 and "mmproj" not in f["path"].lower() and "draft" not in f["path"].lower()]
 
 
+WIKI_URL = "https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip"
+
+
+def ensure_eval(dest_dir):
+    """The held-out corpus for probing, fetched once (1.3 MB)."""
+    import os, zipfile, io
+    path = os.path.join(dest_dir, "wiki.test.raw")
+    if os.path.isfile(path):
+        return path
+    print("[quantprobe auto] fetching the WikiText-2 eval corpus (1.3 MB, one time)...")
+    with urllib.request.urlopen(WIKI_URL, timeout=60) as r:
+        z = zipfile.ZipFile(io.BytesIO(r.read()))
+    with z.open("wikitext-2-raw/wiki.test.raw") as f, open(path, "wb") as out:
+        out.write(f.read())
+    return path
+
+
+def pick_source(files, t):
+    """High-precision source for the custom build: prefer Q8-class (smallest requantizable), else max bits."""
+    cands = []
+    for path, size in files:
+        if "-of-" in path.lower():
+            continue                                # split multi-part files: out of scope for v1
+        bits = size * 8 / (t * 1e9)
+        cands.append((bits, size, path))
+    if not cands:
+        return None
+    hi = sorted([c for c in cands if c[0] >= 7.5], key=lambda c: c[1])
+    return hi[0] if hi else max(cands)
+
+
 def run(a):
     target = a.target
     if target in MODEL_REPOS:
@@ -79,6 +110,40 @@ def run(a):
         raise SystemExit("no usable quant in that repo for this machine")
     scored.sort()
     _, _, path, size, bits, best = scored[0]
+
+    if getattr(a, "custom", False):
+        src = pick_source(files, t)
+        if not src:
+            raise SystemExit("no usable high-precision source in that repo (split files unsupported)")
+        sbits, ssize, spath = src
+        import os
+        dest = getattr(a, "dir", None) or "./models"
+        os.makedirs(dest, exist_ok=True)
+        print("\n[quantprobe auto --custom] source: " + spath + f" ({ssize/1e9:.1f} GB, {sbits:.1f}-bit)")
+        print("  pipeline: fetch source -> probe the fragile band (~30-60 min) -> build the")
+        print("  depth-aware GGUF. Interrupt anytime; the fetch resumes.")
+        if getattr(a, "dry", False):
+            print("  (--dry: nothing downloaded)")
+            return spath
+        from . import fetch as fetchmod
+        if not fetchmod.fetch(repo, dest, spath, fetchmod.token()):
+            raise SystemExit("source download failed (re-run: it resumes)")
+        srcfull = os.path.join(dest, os.path.basename(spath))
+        evalf = ensure_eval(dest)
+        from . import probe as probemod
+        import argparse
+        out = os.path.join(dest, os.path.basename(spath).rsplit(".gguf", 1)[0] + "-depthaware.gguf")
+        pa = argparse.Namespace(gguf=srcfull, bands=4, chunks=32, eval=evalf, ngl=99,
+                                workdir=dest, llama_dir=getattr(a, "llama_dir", None),
+                                apply=True, out=out, dry_run=False)
+        probemod.run(pa)
+        print("\n[quantprobe auto --custom] your personalized model:")
+        print("  quantprobe run --gguf " + out)
+        if getattr(a, "run", False):
+            from . import runtime
+            a.gguf = out; a.bits = None
+            runtime.run(a)
+        return out
     print(f"\n[quantprobe auto] optimizer wants ~{want_bits:g}-bit; closest file in {repo}:")
     print(f"  {path}  ({size/1e9:.1f} GB, {bits:.2f} effective bits)")
     print(f"  predicted on this machine: {best[1]:.1f} tok/s  ({best[0]})")
@@ -96,8 +161,8 @@ def run(a):
     full = os.path.join(dest, os.path.basename(path))
     print(f"\n[quantprobe auto] ready. Run it:")
     print(f"  quantprobe run --gguf {full}")
-    print(f"\n  Want better quality at the SAME size? That's the custom path (the actual product):")
-    print(f"  fetch the f16, then:  quantprobe probe --gguf <f16>.gguf --eval wiki.test.raw --apply")
+    print("\n  Better quality at the SAME size: rerun with --custom - it probes YOUR model's")
+    print("  fragile band (~30-60 min) and builds a depth-aware GGUF personalized to it.")
     if getattr(a, "run", False):
         from . import runtime
         a.gguf = full

{quantprobe-1.5.0 → quantprobe-1.5.1}/quantprobe/cli.py

@@ -99,6 +99,7 @@ def main():
     au.add_argument("--tps", type=float, default=None, help="target tok/s for the optimizer")
     au.add_argument("--max-quality", type=float, default=None)
     au.add_argument("--allow-prune", action="store_true"); au.add_argument("--any-runtime", action="store_true")
+    au.add_argument("--custom", action="store_true", help="THE PRODUCT: fetch a high-precision source, probe YOUR model (~30-60 min), build a depth-aware GGUF personalized to it")
     au.add_argument("--serve", action="store_true", help="with --run: llama-server instead of chat")
     au.add_argument("--extra", default=None)
 

{quantprobe-1.5.0 → quantprobe-1.5.1/quantprobe.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantprobe
-Version: 1.5.0
+Version: 1.5.1
 Summary: Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes.
 Author: Federico Sciuca
 License: MIT
@@ -96,6 +96,7 @@ quantprobe auto qwen3-coder --tps 15 --run   # empty machine -> optimal quant ch
 
 ```bash
 quantprobe auto qwen3-30b --tps 15                       # ONE command: optimizer picks bits, closest quant fetched, run command printed
+quantprobe auto qwen3-30b --custom                       # THE PRODUCT: probe YOUR model, build its personalized depth-aware GGUF
 quantprobe hw                                            # what the law sees on THIS machine (every value source-tagged)
 quantprobe plan     --gguf model.gguf                    # zero-config prediction: placement + tok/s + the launch command
 quantprobe optimize --tps 20                             # CHEAPEST PATH to a target: bits x placement x hardware, Pareto-ranked