初始化项目，由ModelHub XC社区提供模型

Model: ksjpswaroop/zindango-slm
Source: Original Platform

scripts/convert_and_push_gguf.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+"""
+Convert zindango-slm to GGUF and push to Hugging Face.
+
+Requires: llama.cpp cloned, gguf, sentencepiece
+  pip install gguf sentencepiece
+  git clone https://github.com/ggml-org/llama.cpp
+
+Usage:
+  python scripts/convert_and_push_gguf.py [--model-dir PATH] [--quantize Q4_K_M]
+"""
+
+import argparse
+import subprocess
+import sys
+from pathlib import Path
+
+from huggingface_hub import HfApi, create_repo, upload_folder, upload_file
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model-dir", default="outputs/zindango-slm-20260215_124754")
+    parser.add_argument("--llama-cpp", default="/home/piren/projects/llama.cpp")
+    parser.add_argument("--quantize", choices=["q4_k_m", "q5_k_m", "q8_0", "none"], default="none")
+    parser.add_argument("--repo-id", default=None)
+    parser.add_argument("--skip-create", action="store_true")
+    parser.add_argument("--push-only", action="store_true", help="Skip conversion, only push existing GGUF")
+    args = parser.parse_args()
+
+    project_root = Path(__file__).resolve().parent.parent
+    model_dir = project_root / args.model_dir
+    out_dir = project_root / "outputs"
+    f16_gguf = out_dir / "zindango-slm-f16.gguf"
+
+    if not args.push_only:
+        llama_cpp = Path(args.llama_cpp)
+        if not (llama_cpp / "convert_hf_to_gguf.py").exists():
+            raise SystemExit(f"llama.cpp not found at {llama_cpp}. Clone it first.")
+        if not model_dir.exists():
+            raise SystemExit(f"Model not found: {model_dir}")
+
+        # Convert to F16 GGUF
+        cmd = [
+            sys.executable,
+            str(llama_cpp / "convert_hf_to_gguf.py"),
+            str(model_dir),
+            "--outtype", "f16",
+            "--outfile", str(f16_gguf),
+        ]
+        print("Converting to GGUF f16...")
+        subprocess.run(cmd, check=True)
+
+        # Optionally quantize
+        if args.quantize != "none":
+            quant_bin = llama_cpp / "build" / "bin" / "llama-quantize"
+            if not quant_bin.exists():
+                quant_bin = llama_cpp / "bin" / "llama-quantize"
+            if quant_bin.exists():
+                q_gguf = out_dir / f"zindango-slm-{args.quantize}.gguf"
+                cmd = [str(quant_bin), str(f16_gguf), str(q_gguf), args.quantize.upper()]
+                print(f"Quantizing to {args.quantize}...")
+                subprocess.run(cmd, check=True)
+            else:
+                print("llama-quantize not found; skipping quantization")
+
+    # Push to Hub
+    api = HfApi()
+    user = api.whoami()
+    username = user["name"]
+    repo_id = args.repo_id or f"{username}/zindango-slm"
+
+    if not args.skip_create:
+        try:
+            create_repo(repo_id, repo_type="model", exist_ok=True)
+        except Exception as e:
+            if "403" in str(e).lower() or "forbidden" in str(e).lower():
+                print("Create repo failed. Run with --skip-create after creating manually.")
+                raise
+
+    # Upload GGUF file(s): f16 + any quantized (q4_k_m, q8_0, etc.)
+    quant_ggufs = list(out_dir.glob("zindango-slm-q*.gguf")) + list(out_dir.glob("zindango-slm-Q*.gguf"))
+    for gguf_path in [f16_gguf] + quant_ggufs:
+        if gguf_path.exists():
+            print(f"Uploading {gguf_path.name}...")
+            upload_file(
+                path_or_fileobj=str(gguf_path),
+                path_in_repo=gguf_path.name,
+                repo_id=repo_id,
+                repo_type="model",
+                commit_message=f"Add {gguf_path.name}",
+            )
+
+    print(f"Done. Model: https://huggingface.co/{repo_id}")
+
+
+if __name__ == "__main__":
+    main()

scripts/llamacpp_chat.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python3
+"""
+llama.cpp chat with zindango-slm (GGUF) for English chat verification.
+Uses llama-cpp-python with the Q8_0 quantized model from Hugging Face.
+"""
+import os
+import sys
+
+
+def main():
+    try:
+        from llama_cpp import Llama
+    except ImportError:
+        print("llama-cpp-python not installed.")
+        print("Install: pip install llama-cpp-python")
+        print("Or use pre-built wheels: pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu")
+        print("For GPU: pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121")
+        print("\nAlternatively run: ./scripts/llamacpp_chat.sh (requires llama-cli from llama.cpp)")
+        return 1
+
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    project_root = os.path.dirname(script_dir)
+    model_dir = os.path.join(project_root, "models", "zindango-slm")
+    gguf_path = os.path.join(model_dir, "zindango-slm-Q8_0.gguf")
+
+    if not os.path.isfile(gguf_path):
+        print(f"GGUF not found at {gguf_path}")
+        print("Download with: huggingface-cli download ksjpswaroop/zindango-slm zindango-slm-Q8_0.gguf --local-dir models/zindango-slm")
+        os.makedirs(model_dir, exist_ok=True)
+        try:
+            from huggingface_hub import hf_hub_download
+            print("Downloading zindango-slm-Q8_0.gguf from Hugging Face...")
+            path = hf_hub_download(
+                repo_id="ksjpswaroop/zindango-slm",
+                filename="zindango-slm-Q8_0.gguf",
+                local_dir=model_dir,
+                local_dir_use_symlinks=False,
+            )
+            gguf_path = path
+        except Exception as e:
+            print(f"Download failed: {e}")
+            return 1
+
+    print("Loading zindango-slm (Q8_0)...")
+    llm = Llama(
+        model_path=gguf_path,
+        n_ctx=2048,
+        n_threads=os.cpu_count() or 4,
+        chat_format="chatml",
+        verbose=False,
+    )
+
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant. Always respond in English."},
+    ]
+
+    print("\n" + "=" * 60)
+    print("zindango-slm Chat (llama.cpp) - English verification")
+    print("=" * 60)
+    print("Type your message and press Enter. Commands: /quit, /clear")
+    print()
+
+    while True:
+        try:
+            user_input = input("You: ").strip()
+        except (EOFError, KeyboardInterrupt):
+            print("\nBye!")
+            break
+
+        if not user_input:
+            continue
+        if user_input.lower() in ("/quit", "/exit", "quit", "exit"):
+            print("Bye!")
+            break
+        if user_input.lower() == "/clear":
+            messages = [messages[0]]
+            print("[Context cleared]")
+            continue
+
+        messages.append({"role": "user", "content": user_input})
+
+        print("Assistant: ", end="", flush=True)
+        stream = llm.create_chat_completion(
+            messages=messages,
+            max_tokens=512,
+            temperature=0.7,
+            stream=True,
+        )
+        full_reply = ""
+        for chunk in stream:
+            delta = chunk["choices"][0].get("delta", {})
+            content = delta.get("content", "")
+            if content:
+                print(content, end="", flush=True)
+                full_reply += content
+        print()
+
+        if full_reply:
+            messages.append({"role": "assistant", "content": full_reply})
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/llamacpp_chat.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# llama.cpp chat with zindango-slm for English verification
+# Prerequisites: llama.cpp built (llama-cli) and GGUF model
+
+set -e
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(dirname "$SCRIPT_DIR")"
+MODEL_DIR="${MODEL_DIR:-$PROJECT_ROOT/models/zindango-slm}"
+GGUF="${GGUF:-$MODEL_DIR/zindango-slm-Q8_0.gguf}"
+LLAMA_CLI="${LLAMA_CLI:-llama-cli}"
+
+if ! command -v "$LLAMA_CLI" &>/dev/null; then
+    echo "llama-cli not found. Build llama.cpp or set LLAMA_CLI:"
+    echo "  git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make"
+    exit 1
+fi
+
+if [[ ! -f "$GGUF" ]]; then
+    echo "GGUF not found. Downloading..."
+    mkdir -p "$MODEL_DIR"
+    huggingface-cli download ksjpswaroop/zindango-slm zindango-slm-Q8_0.gguf --local-dir "$MODEL_DIR" || exit 1
+fi
+
+echo "=== zindango-slm Chat (llama.cpp) - English verification ==="
+exec "$LLAMA_CLI" -m "$GGUF" -c 2048 -i

scripts/push_scripts_to_hub.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+"""
+Push zindango-slm scripts to Hugging Face model repo (scripts/ folder).
+
+Usage:
+  python scripts/push_scripts_to_hub.py [--repo-id USERNAME/zindango-slm]
+"""
+
+import argparse
+from pathlib import Path
+
+from huggingface_hub import HfApi, create_repo, upload_file
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--repo-id", default=None)
+    parser.add_argument("--skip-create", action="store_true")
+    args = parser.parse_args()
+
+    sft_root = Path(__file__).resolve().parent.parent
+    benchmark_root = sft_root.parent / "nanbeige-benchmark-verification"
+
+    api = HfApi()
+    user = api.whoami()
+    username = user["name"]
+    repo_id = args.repo_id or f"{username}/zindango-slm"
+
+    if not args.skip_create:
+        try:
+            create_repo(repo_id, repo_type="model", exist_ok=True)
+        except Exception as e:
+            if "403" in str(e).lower() or "forbidden" in str(e).lower():
+                print("Create repo failed. Run with --skip-create.")
+                raise
+
+    scripts_to_upload = [
+        (sft_root / "scripts/convert_and_push_gguf.py", "scripts/convert_and_push_gguf.py"),
+        (sft_root / "scripts/push_to_hub.py", "scripts/push_to_hub.py"),
+        (sft_root / "scripts/push_scripts_to_hub.py", "scripts/push_scripts_to_hub.py"),
+        (benchmark_root / "scripts/test_zindango_gguf.py", "scripts/test_zindango_gguf.py"),
+        (benchmark_root / "scripts/llamacpp_chat.py", "scripts/llamacpp_chat.py"),
+        (benchmark_root / "scripts/llamacpp_chat.sh", "scripts/llamacpp_chat.sh"),
+    ]
+
+    for local_path, path_in_repo in scripts_to_upload:
+        if not local_path.exists():
+            print(f"Skipping {local_path} (not found)")
+            continue
+        print(f"Uploading {path_in_repo}...")
+        upload_file(
+            path_or_fileobj=str(local_path),
+            path_in_repo=path_in_repo,
+            repo_id=repo_id,
+            repo_type="model",
+            commit_message=f"Add {path_in_repo}",
+        )
+
+    print(f"Done. https://huggingface.co/{repo_id}")
+
+
+if __name__ == "__main__":
+    main()

scripts/push_to_hub.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+Push zindango-slm to Hugging Face Hub.
+Usage:
+  python scripts/push_to_hub.py [--model-dir PATH] [--repo-id USERNAME/zindango-slm]
+Requires: huggingface-cli login (or HF_TOKEN env)
+"""
+
+import argparse
+from pathlib import Path
+
+from huggingface_hub import HfApi, create_repo, upload_folder
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Push zindango-slm to Hugging Face Hub")
+    parser.add_argument(
+        "--model-dir",
+        type=str,
+        default="outputs/zindango-slm-20260215_124754",
+        help="Local model directory to upload",
+    )
+    parser.add_argument(
+        "--repo-id",
+        type=str,
+        default=None,
+        help="Hub repo ID (username/zindango-slm). Default: infer from login",
+    )
+    parser.add_argument(
+        "--private",
+        action="store_true",
+        help="Create private repository",
+    )
+    parser.add_argument(
+        "--skip-create",
+        action="store_true",
+        help="Skip create_repo (use if repo already exists or create manually at https://huggingface.co/new)",
+    )
+    args = parser.parse_args()
+
+    model_dir = Path(args.model_dir)
+    if not model_dir.exists():
+        raise SystemExit(f"Model directory not found: {model_dir}")
+
+    api = HfApi()
+    try:
+        user = api.whoami()
+        username = user["name"]
+    except Exception as e:
+        raise SystemExit(
+            f"Not logged in to Hugging Face. Run: huggingface-cli login\nError: {e}"
+        )
+
+    repo_id = args.repo_id or f"{username}/zindango-slm"
+    print(f"Uploading to https://huggingface.co/{repo_id}")
+
+    # Create repo if needed (skip if --skip-create or 403)
+    if not args.skip_create:
+        try:
+            create_repo(repo_id, repo_type="model", private=args.private, exist_ok=True)
+        except Exception as e:
+            err = str(e).lower()
+            if "403" in err or "forbidden" in err or "rights" in err:
+                print("Note: Could not create repo (check token write access).")
+                print("Create it manually at: https://huggingface.co/new")
+                print("Then run with: --skip-create")
+                raise
+            if "already exists" not in err and "409" not in err:
+                raise
+
+    # Exclude checkpoint subdir and training artifacts
+    ignore_patterns = ["checkpoint-*", "training_args.bin", "*.pt", ".git*"]
+
+    upload_folder(
+        folder_path=str(model_dir),
+        repo_id=repo_id,
+        repo_type="model",
+        ignore_patterns=ignore_patterns,
+        commit_message="Upload zindango-slm: SFT for Zindango (English-only)",
+    )
+    print(f"Done. Model: https://huggingface.co/{repo_id}")
+
+
+if __name__ == "__main__":
+    main()

scripts/test_zindango_gguf.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python3
+"""
+Test zindango-slm: GGUF (llama-cpp-python) or HF (transformers) fallback.
+Runs a single prompt to verify the model loads and generates.
+"""
+import os
+import sys
+
+
+def test_gguf(gguf_path: str) -> bool:
+    """Test via llama-cpp-python if available."""
+    try:
+        from llama_cpp import Llama
+    except ImportError:
+        return False
+
+    print("Loading zindango-slm (GGUF) with llama-cpp-python...")
+    llm = Llama(
+        model_path=gguf_path,
+        n_ctx=512,
+        n_threads=os.cpu_count() or 4,
+        chat_format="chatml",
+        verbose=False,
+    )
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant. Reply briefly."},
+        {"role": "user", "content": "Who are you? One sentence only."},
+    ]
+    out = llm.create_chat_completion(messages=messages, max_tokens=64, temperature=0.7)
+    reply = out["choices"][0]["message"]["content"]
+    print("Reply:", reply)
+    return bool(reply.strip())
+
+
+def test_transformers(local_path: str | None = None) -> bool:
+    """Test via transformers (HF model) as fallback when GGUF/llama.cpp unavailable."""
+    try:
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+    except ImportError:
+        print("transformers not installed: pip install transformers torch")
+        return False
+
+    model_id = local_path if local_path and os.path.isdir(local_path) else "ksjpswaroop/zindango-slm"
+    print(f"Testing zindango-slm (transformers) - fallback when llama-cpp unavailable...")
+    tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_id,
+        trust_remote_code=True,
+        torch_dtype="auto",
+        low_cpu_mem_usage=True,
+    )
+    messages = [{"role": "user", "content": "Who are you? One sentence only."}]
+    text = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+    inputs = tokenizer(text, return_tensors="pt")
+    out = model.generate(
+        **inputs, max_new_tokens=64, pad_token_id=tokenizer.pad_token_id or tokenizer.eos_token_id
+    )
+    reply = tokenizer.decode(
+        out[0][inputs["input_ids"].shape[1] :], skip_special_tokens=True
+    )
+    print("Reply:", reply)
+    return bool(reply.strip())
+
+
+def main():
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    project_root = os.path.dirname(script_dir)
+    model_dir = os.path.join(project_root, "models", "zindango-slm")
+
+    # Prefer Q8_0, then f16
+    for name in ("zindango-slm-Q8_0.gguf", "zindango-slm-f16.gguf"):
+        gguf_path = os.path.join(model_dir, name)
+        if os.path.isfile(gguf_path):
+            print(f"Trying GGUF: {gguf_path}")
+            if test_gguf(gguf_path):
+                print("\n[OK] zindango-slm GGUF test passed.")
+                return 0
+            break
+
+    print("\nllama-cpp-python unavailable or failed. Using transformers fallback...")
+    local_hf = os.path.join(project_root, "models", "zindango-slm-hf")
+    if test_transformers(local_hf):
+        print("\n[OK] zindango-slm transformers test passed.")
+        return 0
+
+    print("\n[FAIL] No working backend. Install: pip install transformers torch")
+    print("For GGUF: pip install llama-cpp-python")
+    return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())