Delete results/strict_headline.json with huggingface_hub

results/strict_headline.json

@@ -1,214 +0,0 @@
-{
- "config": {
-  "model": "/root/models/minicpm-v4.7-35b-a3b-q4_k_m.gguf",
-  "bins": "['base=/root/app/llama.cpp/build/bin/epq-chat']",
-  "bin": "",
-  "rounds": "9",
-  "strict_mb": "8192",
-  "strict_data_mb": "0",
-  "metric": "anon",
-  "cli": "chat",
-  "ram_budget_mb": "0",
-  "ctx": "4096",
-  "threads": "8",
-  "ubatch": "128",
-  "n_predict": "48",
-  "no_prefetch": "False",
-  "no_lock": "False",
-  "extra": "[]",
-  "label": "headline",
-  "workdir": "/tmp/bench",
-  "keep_text": "False"
- },
- "results": [
-  {
-   "arm": "base",
-   "round": 0,
-   "wall_s": 12.26,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7781.2,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7642.9,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1321.9,
-   "decode_tokens": 47,
-   "decode_s": 7.09,
-   "decode_tok_s": 6.63,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 68.6775,
-   "ssd_mb_per_token": 220.29495239257812,
-   "prefetch_used_pct": 0,
-   "stdout_tail": "ixture-of-Experts (MoE) models route tokens by using a lightweight gating network to dynamically select a small subset of specialized \"expert\"在  $100 \\mathrm{~m"
-  },
-  {
-   "arm": "base",
-   "round": 1,
-   "wall_s": 13.43,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7799.5,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7650.5,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1321.9,
-   "decode_tokens": 47,
-   "decode_s": 7.57,
-   "decode_tok_s": 6.21,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 72.1095,
-   "ssd_mb_per_token": 192.59357452392578,
-   "prefetch_used_pct": 0,
-   "stdout_tail": ".gguf\n[sdq] ctx=4096  threads=8  ubatch=128  RAM(RSS)=8568 MB  模型載入 0.7s\nassistant: 1. **CPU** 是電腦的「大腦」，負責執行所有運算與指令，但本身不儲存大量資料。\n2. **RAM** 是「短期工作記憶」，存放 CPU 正在處理"
-  },
-  {
-   "arm": "base",
-   "round": 2,
-   "wall_s": 12.62,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7799.5,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7650.5,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1322.1,
-   "decode_tokens": 47,
-   "decode_s": 7.42,
-   "decode_tok_s": 6.34,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 68.6112,
-   "ssd_mb_per_token": 214.11705017089844,
-   "prefetch_used_pct": 0,
-   "stdout_tail": "*Analyze the Request:**\n    *   Task: List five daily work tasks that involve using a computer.\n    *   Constraint: Each task must be explained in one sentence."
-  },
-  {
-   "arm": "base",
-   "round": 3,
-   "wall_s": 15.36,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7781.6,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7642.9,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1321.8,
-   "decode_tokens": 47,
-   "decode_s": 9.05,
-   "decode_tok_s": 5.19,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 68.6775,
-   "ssd_mb_per_token": 220.29495239257812,
-   "prefetch_used_pct": 0,
-   "stdout_tail": "ixture-of-Experts (MoE) models route tokens by using a lightweight gating network to dynamically select a small subset of specialized \"expert\"在  $100 \\mathrm{~m"
-  },
-  {
-   "arm": "base",
-   "round": 4,
-   "wall_s": 13.22,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7799.1,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7650.5,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1322.1,
-   "decode_tokens": 47,
-   "decode_s": 8.13,
-   "decode_tok_s": 5.78,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 72.1152,
-   "ssd_mb_per_token": 192.5516128540039,
-   "prefetch_used_pct": 0,
-   "stdout_tail": ".gguf\n[sdq] ctx=4096  threads=8  ubatch=128  RAM(RSS)=8568 MB  模型載入 0.7s\nassistant: 1. **CPU** 是電腦的「大腦」，負責執行所有運算與指令，但本身不儲存大量資料。\n2. **RAM** 是「短期工作記憶」，存放 CPU 正在處理"
-  },
-  {
-   "arm": "base",
-   "round": 5,
-   "wall_s": 14.53,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7799.2,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7650.5,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1322.1,
-   "decode_tokens": 47,
-   "decode_s": 8.67,
-   "decode_tok_s": 5.42,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 68.617,
-   "ssd_mb_per_token": 214.07604217529297,
-   "prefetch_used_pct": 0,
-   "stdout_tail": "*Analyze the Request:**\n    *   Task: List five daily work tasks that involve using a computer.\n    *   Constraint: Each task must be explained in one sentence."
-  },
-  {
-   "arm": "base",
-   "round": 6,
-   "wall_s": 15.05,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7781.2,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7642.9,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1321.6,
-   "decode_tokens": 47,
-   "decode_s": 8.9,
-   "decode_tok_s": 5.28,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 68.6717,
-   "ssd_mb_per_token": 220.3378677368164,
-   "prefetch_used_pct": 0,
-   "stdout_tail": "ixture-of-Experts (MoE) models route tokens by using a lightweight gating network to dynamically select a small subset of specialized \"expert\"在  $100 \\mathrm{~m"
-  },
-  {
-   "arm": "base",
-   "round": 7,
-   "wall_s": 13.28,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7799.3,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7650.5,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1322.1,
-   "decode_tokens": 47,
-   "decode_s": 7.51,
-   "decode_tok_s": 6.26,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 72.1209,
-   "ssd_mb_per_token": 192.51060485839844,
-   "prefetch_used_pct": 0,
-   "stdout_tail": ".gguf\n[sdq] ctx=4096  threads=8  ubatch=128  RAM(RSS)=8568 MB  模型載入 0.8s\nassistant: 1. **CPU** 是電腦的「大腦」，負責執行所有運算與指令，但本身不儲存大量資料。\n2. **RAM** 是「短期工作記憶」，存放 CPU 正在處理"
-  },
-  {
-   "arm": "base",
-   "round": 8,
-   "wall_s": 14.18,
-   "returncode": 0,
-   "strict_ok": true,
-   "peak_anon_mb": 7799.1,
-   "peak_swap_mb": 0.0,
-   "vm_lck_mb": 7650.5,
-   "swap_samples_over_zero": 0,
-   "peak_file_mb": 1322.4,
-   "decode_tokens": 47,
-   "decode_s": 8.07,
-   "decode_tok_s": 5.83,
-   "slots": 3714,
-   "arena_gib": 6.35,
-   "hit_rate_pct": 68.617,
-   "ssd_mb_per_token": 214.07604217529297,
-   "prefetch_used_pct": 0,
-   "stdout_tail": "*Analyze the Request:**\n    *   Task: List five daily work tasks that involve using a computer.\n    *   Constraint: Each task must be explained in one sentence."
-  }
- ]
-}