diff --git a/Makefile b/Makefile index 75427c9..91da4b4 100644 --- a/Makefile +++ b/Makefile @@ -12,7 +12,7 @@ help: @echo "build-config-dry generate YAML via API (requires token; never creates task)" @echo "probe-readonly authenticated read-only task/page GET" @echo "dry-run-pending read-only adapt pending A→B report" - @echo "test stdlib unit tests + local SIGTERM integration (needs sockets)" + @echo "test stdlib unit tests + offline SIGTERM integration" @echo "build Docker build using platform base (needs Docker + TCR access)" @echo "smoke-health local HTTP smoke (needs sockets; default test STRATEGY_ID)" @echo "dry-run read-only pending report (example fallback)" diff --git a/README.md b/README.md index 2428aa0..0f2cf87 100644 --- a/README.md +++ b/README.md @@ -20,9 +20,12 @@ Victor 的确认已内置，`LIVE_CONFIRM` 仍接受但不再必需。每次 tas `LIVE_QUEUE_THRESHOLD=95`（严格小于），`LIVE_MAX_SUBMITS_PER_CYCLE=3`， `LIVE_CYCLE_SECONDS=600`（最小 60 秒）。环境队列提示仅可额外阻塞。 候选来自 `PENDING_SUBMIT_MD` / `PENDING_SUBMIT_TXT`，否则使用 -`src/data/pending-submit.md`（若存在）；A verified_reuse → 其他 A → B。 -禁提、重复、GPU 未映射、占位符候选跳过。`LIVE_STATE_FILE` 默认 -`/tmp/live-submitted.json`，在请求前持久化去重；失败请求也不自动重试。 +`src/data/candidates.json`（随镜像内置）；A verified_reuse → 其他 A → B。 +禁提、重复、GPU 未映射、占位符候选跳过。按 try_next_gpus 顺序选择首个已映射且未提交的模型/GPU 对。`LIVE_STATE_FILE` 默认 +`/tmp/live-submitted.json`，格式为 `model|gpuEnum` 字符串列表，在请求前持久化；失败请求也不自动重试。旧版仅模型名状态文件须先离线迁移，否则 fail closed。 +去重合并远端全部状态的 `modelId` + `gpuType`、内置 `src/data/submitted-ledger.json` 和持久化状态。A 允许同模型换 GPU；do-not-resubmit 模型跨 GPU 全禁。服务启动重建一次并只记录三类 pair 数；每次提交前刷新远端，失败则 hold `ledger_rebuild_failed`。task/page total 接受非负整数或 ASCII 数字字符串。 +凭证优先级：`EXTERNAL_SERVICE_TOKEN` → `XC_TOKEN_FILE` → `XC_TOKEN` → `MODELHUB_XC_TOKEN`；跳过空值和占位符。每周期只记录 source 环境变量名，使用 `Xc-Token` 请求头，不记录凭证值。 +离线再生成：`python3 scripts/bake_candidates.py`、`python3 scripts/bake_ledger.py`，读取 `/workspace/modelhub-adapt` 本地文件；候选 342（A 46、B 296），ledger 206 对及 28 个模型禁提项。 配置优先 build-config，失败使用 sample 并记录来源及原因。token 缺失只 hold。 ## 快速开始 diff --git a/docs/gpu-perf-order.md b/docs/gpu-perf-order.md index e252d1a..c42a34e 100644 --- a/docs/gpu-perf-order.md +++ b/docs/gpu-perf-order.md @@ -19,8 +19,8 @@ |-----------------|------------|------------------------------|------| | 1（一梯队并列） | 壁砺166M | `Biren_166m` | ≈ 曦望 S2；社区成功量壁砺更高 | | 1（一梯队并列） | 曦望 S2 | `Sunrise_pt-200-x1`（抓包证实） | 与壁砺并列，勿臆造先后「性能」 | -| 2 | 天垓150 | Iluvatar 天垓族（字符串待核） | 条件回退；饱和+唯一性碰撞多 | -| 3 | 天垓100 | （待核） | 一般不扇出 | +| 2 | 天垓150 | Iluvatar_bi-150 | 条件回退；饱和+唯一性碰撞多 | +| 3 | 天垓100 | Iluvatar_bi-100 | 一般不扇出 | | 4 | 智铠 mrv-100 | `Iluvatar_mrv-100` | 我方唯一成功样本族；不当最快卡宣传 | 并列一梯队时：若 pending `try-next` 已给出相对顺序则保留；否则可按「壁砺 / 曦望」与池内缺口并列候选，报告标 `order_source=experience`。 @@ -44,7 +44,8 @@ - 结论：**API**，未公开文档但已抓包证实，依据 [autoconfig-capture-2026-10-16.md](/workspace/modelhub-adapt/logs/autoconfig-capture-2026-10-16.md)。 - `POST /api/adapt/task/build-config`，query 为 `gpuType` / `framework` / `taskType`，空 body；成功 JSON `code=0`，`data` 为 YAML。 - UI 无「自动配置」标签；选择框架触发 effect 填入 configParams。模型地址不进入该请求。 -- 抓包观察 Authorization（值未记录）；容器默认 Xc-Token 社区实践，可显式切换 Authorization，尚无 token 鉴权实证。 +- 2026-10-17 主机只读探针确认 task/page 使用 Xc-Token 成功；容器继续使用 Xc-Token，Authorization Bearer 属于浏览器路径。 +- 已核对 GPU 枚举：天垓100=Iluvatar_bi-100，天垓150=Iluvatar_bi-150，智铠100=Iluvatar_mrv-100，MTT S4000/摩尔线程=Mthreads_s4000；保留壁砺及曦望映射。枚举证据不代表官方性能排序。 - 默认 dry-run：`resolve_token()` 成功时优先 build-config；失败回退 sample，逐条报告 configParams_source、GAP 和 fallback reason。无 token → sample。CONFIG_PARAMS_SOURCE=sample 强制离线；=build-config 强制 API 路径（dry-run with_meta 仍可回退）。make build-config-dry 保持失败非零退出。 - API gpuType 仅映射壁砺/壁砺166M/Biren_166m 与曦望/曦望 S2/Sunrise_pt-200-x1；未知卡不请求 API，报告 GAP: gpu enum unmapped。 - 选策优化后仍为 experience_order，perf_order=unset；order_source=experience；无正式性能表。Section A 仅按 foothold 文本将 verified_reuse 提前，其余 A 保持文件序，再接 B。API foothold evidence: GAP (not wired)。 diff --git a/reports/live-gate-summary.md b/reports/live-gate-summary.md index b2e86dd..7b079f6 100644 --- a/reports/live-gate-summary.md +++ b/reports/live-gate-summary.md @@ -1,27 +1,11 @@ -# Queue-gated live submit +# Live gate update — 2026-10-17 -Victor-approved live defaults on. ALLOW_LIVE_SUBMIT=0 stops submission; -STRATEGY_ID remains mandatory. LIVE_CONFIRM is accepted but optional. +Queue snapshots accept integer or ASCII digit-string totals and derive model/GPU pairs from modelId and gpuType across all statuses. Nonterminal tasks count toward the queue gate. Invalid or incomplete snapshots stop submissions with ledger_rebuild_failed. -Each add requires a fresh authenticated onlyMine task/page snapshot, complete -through data.total (maximum 20 pages). All nonterminal records count; -queue >= LIVE_QUEUE_THRESHOLD (default 95) stops the cycle. Authentication, -transport, HTTP, platform, JSON and pagination errors fail closed. Environment -queue hints can only add blockers. +Token resolution prefers EXTERNAL_SERVICE_TOKEN, XC_TOKEN_FILE, XC_TOKEN, then MODELHUB_XC_TOKEN; empty and placeholder credentials are skipped. Missing credentials hold even with injected submit clients. Each allowed cycle logs only the selected source name. Xc-Token remains the authentication header. -Cycles prioritize Section A verified_reuse, other A, then B; reject banned -families, unmapped GPUs and placeholders; use build-config with recorded sample -fallback; reserve model identity in memory and LIVE_STATE_FILE before calling -TaskAddClient. Remote task identities also block duplicates. Default cap is 3 -attempts per cycle. Failed calls retain their reservations to prevent retries. -The state file defaults to /tmp/live-submitted.json; preserve or mount it for -restart durability beyond ephemeral container storage. +Offline generators read local adapt evidence only. Input candidates: A=60, B=296; after pending and banned filters: A=46, B=296, total=342. Verified reuse A precedes other A, then B. Baked ledger: 206 pairs and 28 blocked models. Baked JSON ships through COPY src/; .dockerignore does not exclude src/data/*.json. -Server runs a daemon worker every 600 seconds (minimum 60), using the shutdown -Event for interruptible waits. Missing credentials hold instead of crashing. -Docker FROM is unchanged; templates are copied for runtime fallback. +The ledger merges remote pairs, baked pairs, and persisted model|gpu pairs. Explicit do-not-resubmit models are blocked on every GPU; other models may use the next mapped, unsubmitted GPU in candidate order. Reservations are written before task/add, including failed attempts. Legacy model-only state files fail closed and require offline migration. Startup rebuild logs source counts; each prospective submission refreshes remote identities and queue count. -Validation: make test passes 54 tests, including mocked platform calls and local -SIGTERM integration. Sandbox initially denied local sockets; the suite passed -with local socket permission. No real ModelHub calls, token writes, commits, -tags or pushes were performed. +Validation: make test passes 59 tests using stdlib only. Added coverage for pair dedupe and restart persistence, baked blocks, next-GPU selection, missing tokens, token source logging, digit-string totals, invalid totals, and baked candidate ordering/filtering. SIGTERM uses a mocked HTTP server and real subprocess signal without network calls. Dockerfile FROM unchanged. No git commit, push, tag, live probe, build-config call, or live submission performed. diff --git a/scripts/bake_candidates.py b/scripts/bake_candidates.py new file mode 100644 index 0000000..5579cfa --- /dev/null +++ b/scripts/bake_candidates.py @@ -0,0 +1,23 @@ +"""Bake the local pending pool without network access.""" +import json +import sys +from collections import Counter +from pathlib import Path +sys.path.insert(0, str(Path(__file__).resolve().parents[1])) +from src.pending_pool import build_ordered_candidates +from src.banned import banned_rule + + +def main(): + rows = build_ordered_candidates('/workspace/modelhub-adapt/pending-submit.md', '/workspace/modelhub-adapt/pending-submit.txt') + print('input', dict(Counter(r['section'] for r in rows))) + rows = [dict(model_address=r['model_address'], section=r['section'], foothold_class=r['foothold_class'], try_next_gpus=r['try_next_gpus'], framework='vllm') for r in rows if not r['skip_reason'] and not banned_rule(r['model_address'])] + rows.sort(key=lambda r: (r['section'] != 'A', r['foothold_class'] != 'verified_reuse')) + output = Path(__file__).resolve().parents[1] / 'src/data/candidates.json' + output.parent.mkdir(exist_ok=True) + output.write_text(json.dumps(rows, ensure_ascii=False, indent=2) + '\n') + print('baked', dict(Counter(r['section'] for r in rows)), 'total', len(rows)) + + +if __name__ == '__main__': + main() diff --git a/scripts/bake_ledger.py b/scripts/bake_ledger.py new file mode 100644 index 0000000..6ff3d9c --- /dev/null +++ b/scripts/bake_ledger.py @@ -0,0 +1,39 @@ +"""Extract only model/GPU identities from local evidence; never copy raw fields.""" +import json +import re +import sys +from pathlib import Path +sys.path.insert(0, str(Path(__file__).resolve().parents[1])) +from src.config_params import GPU_ENUMS +from src.live_queue import model_key +from src.pending_pool import load_do_not_resubmit + + +def extract(value, source, pairs): + if isinstance(value, dict): + model = value.get('modelId') or value.get('model') or value.get('model_address') + gpu = value.get('gpuType') or value.get('gpu_code') or value.get('gpu') or value.get('gpuLabel') + if isinstance(model, str) and re.fullmatch(r'[\w.-]+/[\w.\-/]+', model) and isinstance(gpu, str) and gpu in GPU_ENUMS: + pairs.setdefault((model_key(model), GPU_ENUMS[gpu]), source) + for child in value.values(): + extract(child, source, pairs) + elif isinstance(value, list): + for child in value: + extract(child, source, pairs) + + +def main(): + base = Path('/workspace/modelhub-adapt') + files = [base / 'logs/task-page-snapshot-2026-10-17.json', *sorted((base / 'logs').glob('submit-session-*.json')), *sorted((base / 'logs').glob('submit-batch-*.json'))] + pairs = {} + for path in files: + extract(json.loads(path.read_text()), path.name, pairs) + blocks = sorted(map(model_key, load_do_not_resubmit(base / 'do-not-resubmit.md'))) + output = Path(__file__).resolve().parents[1] / 'src/data/submitted-ledger.json' + output.parent.mkdir(exist_ok=True) + output.write_text(json.dumps(dict(pairs=[dict(model=m, gpu=g, source=s) for (m,g),s in sorted(pairs.items())], blocked_models=blocks), indent=2) + '\n') + print('baked pairs', len(pairs), 'blocked models', len(blocks)) + + +if __name__ == '__main__': + main() diff --git a/src/config_params.py b/src/config_params.py index fa365dd..9763feb 100644 --- a/src/config_params.py +++ b/src/config_params.py @@ -10,6 +10,11 @@ GPU_ENUMS = { '壁砺': 'Biren_166m', '壁砺166M': 'Biren_166m', 'Biren_166m': 'Biren_166m', '曦望': 'Sunrise_pt-200-x1', '曦望 S2': 'Sunrise_pt-200-x1', 'Sunrise_pt-200-x1': 'Sunrise_pt-200-x1', + '天垓100': 'Iluvatar_bi-100', 'Iluvatar_bi-100': 'Iluvatar_bi-100', + '天垓150': 'Iluvatar_bi-150', 'Iluvatar_bi-150': 'Iluvatar_bi-150', + '智铠': 'Iluvatar_mrv-100', '智铠100': 'Iluvatar_mrv-100', + '智铠 mrv-100': 'Iluvatar_mrv-100', 'Iluvatar_mrv-100': 'Iluvatar_mrv-100', + 'MTT S4000': 'Mthreads_s4000', '摩尔线程': 'Mthreads_s4000', 'Mthreads_s4000': 'Mthreads_s4000', } diff --git a/src/data/candidates.json b/src/data/candidates.json new file mode 100644 index 0000000..dc37e01 --- /dev/null +++ b/src/data/candidates.json @@ -0,0 +1,3661 @@ +[ + { + "model_address": "open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr2e-05_beta0.5_alpha1_epoch10", + "section": "A", + "foothold_class": "verified_reuse", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "quotientai/limbic-tool-use-0.5B-32K", + "section": "A", + "foothold_class": "verified_reuse", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "varunchundru/dpo-qwen2.5-0.5b-halueval", + "section": "A", + "foothold_class": "verified_reuse", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "1000kavya/SmolLM2-135M-Alpaca-SFT", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "BanglaLLM/BanglaLLama-3.2-1b-unolp-culturax-base-v0.0.1", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Chloemp/smollm2-135m-xlam-fullft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Farhankhan1/deepseek-r1-distill-qwen-1.5b-reasoning-finetune", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Fian1928/Qwen2.5-0.5B-Instruct-legal-alpaca-id-finetuned", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Firemedic15/qwen2.5-0.5b-ft-matched-merged", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JaeWooShin/qwen2.5-math-1.5b-fewgt-u1-n256-inverted-lam1-s0", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoGuiAlves/thagiPo-llama3.2-1B-math", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "KingNish/Qwen2.5-0.5b-Test-ft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "LouieR09112/WikiAI1.5B", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "MadeAgents/Hammer2.0-0.5b", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "MadeAgents/Hammer2.1-0.5b", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "NotASI/Qwen2-0.5B-Math", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ryder99/Llama-3.2-1B-Instruct-Arabic-360s", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Sakalti/mont-normal", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "SakanaAI/TAID-LLM-1.5B", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Sky-06/qwen2.5-coder-1.5b-agentic-sft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "SultanR/SmolTulu-1.7b-Instruct", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Wenboz/UOPD-Qwen2.5-1.5B-Instruct-WebShop", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-quality-bleu", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "abaryan/CyberXP_Agent_Llama_3.2_1B", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "apiskecil/qwen2.5-1.5b-legal-id-sft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "armandosj85/Qwen2.5-1.5B-Instruct-DPO", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "banhcarrot/qwen2.5-0.5b-networkadmin-sft-merged", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "曦望", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "dphn/dolphin-2.9.3-qwen2-1.5b", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "erkenovaj/strong_tofu_Qwen2.5-1.5B-Instruct_full", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "halcyon-llm/SmolLM2-360M-japanese_token-11403", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "interpretable-finetuning/qwen2.5-1.5b-unaliased", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "jasirjru/DomainTune-Qwen2.5-1.5B-Triage", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mnoukhov/SmolLM2-135M-Instruct_tldr-sft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "nyuuzyou/SmolLM2-360M-Eagle", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "pngwn/SmolLM2-135M-Capybara-SFT", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "曦望", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "poco28/qwen2.5-0.5b-math-sft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "rnnandi/bangla-smollm-135m", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "曦望", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sirsqm/seger-qwen2.5-0.5b", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "swathikchhuggingface/ticket-triage-qwen2.5-1.5b-merged", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sxiong/MLR_executor_Qwen-1.5B", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "tayaee/Qwen2.5-1.5B-Korean-SFT-smoke", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "yanggangu/Llama-3.2-1B-Instruct-FT-ScienceQA", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "zuxler/qwen2.5-1.5b-indonesian-legal-sft", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mondk/Claude-smolLM2-2B.safetensors", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer5_scoeff100_epoch10", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "prithivMLmods/Qwen2.5-1.5B-DeepSeek-R1-Instruct", + "section": "A", + "foothold_class": "in_flight", + "try_next_gpus": [ + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mesolitica/Malaysian-Llama-3.2-1B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "DeepAuto-AI/Explore_Llama-3.2-1B-Inst", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "prithivmlmods/qwen2.5-1.5b-deepseek-r1-instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "jaeyong2/qwen2.5-0.5b-instruct-ja-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "stratosphere/qwen2.5-1.5b-slips-immune-summarization", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "nakue/qwen2.5-0.5b-funccall", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "zchjkhzkhc/Llama-3.2-1B-vietnamese-diffusion", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "melikegks/turkish-pii-guard-qwen2.5-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "agentlans/SmolLM2-135M-multilingual-base", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "tayaee/qwen2.5-1.5b-instruct-ko-reasoning-alpha-smoke", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "heimai/Industrial_and_Scientific_Qwen2.5_0.5B_sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "jamal-ibrahim/qwen2.5-1.5b-json-repair", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "pkupie/Qwen2.5-1.5B-bo-cpt", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "EphAsad/Atem-SageMaths-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ryder99/Llama-3.2-1B-Instruct-Hindi", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "jwhj/Qwen2.5-Math-1.5B-OREO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "iromu/Qwen2.5-1.5B-k3", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "LIF1014/ptdbench-Qwen2.5-0.5B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ahgsgsh/deepseek-r1-distill-qwen-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "rishitavenkat2812/smollm2-135m-instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "geraldot/qwen-alpaca-indonesia", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "junie626/qwen2.5-1.5b-instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "bbidpa/Qwen2.5-Coder-0.5B-Flutter-direct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "wwwcomcom/ko-morph-qwen2.5-0.5b-instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "roaminwind/deepseek-r1-distill-qwen-1.5b-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "MedGm/Llama-Locali-Qwen2.5-Coder-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "CleytonNobre/Qwen2.5-0.5B-Instruct-AB-Map", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "AITeamVN/Vi-Qwen2-1.5B-RAG", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "saurabhb2412/qwen2.5-1.5b-ddx-ranker", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Sheikhaei/llama-3.2-1b-english-persian-translator", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sail/Sailor-0.5B-Chat", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mohamedahmedae/llama-3.2-1b-instruct-medical-finetuned-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "AlexanderWang915/qwen2.5-1.5b-moloptins", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "agentlans/Qwen2.5-1.5B-Instruct-Multiple-Choice-Maker", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "pkupie/Qwen2.5-1.5B-kk-cpt", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "EphAsad/Atem-SageCoder-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "iromu/Qwen2.5-1.5B-tools", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "LIF1014/ptdbench-Llama-3.2-1B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "bbidpa/Qwen2.5-Coder-0.5B-Flutter-steps", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "wwwcomcom/ko-morph-qwen2.5-0.5b-cpt", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "CleytonNobre/Qwen2.5-1.5B-Instruct-AB-Map", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "EphAsad/Atem-Wisdom-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "EphAsad/Atem-v1-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ma7ee7/SmolLM2-135M-Reasoning-5K", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Liang0223/Qwen-2.5-Math-1.5B-DFT", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Luigi/SmolLM2-135M-Instruct-TaiwanChat", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Nanthasit/sakthai-context-1.5b-merged-v2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "RecursiveMAS/Sequential-Light-Solver-Qwen2.5-Math-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Bernadetta14/qwen2.5-coder-0.5b-vulnerability-detector", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "andyx10/Qwen2.5-1.5B-Instruct-NLA-L18-av", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Etherll/Qwen2.5-Coder-1.5B-CodeFIM", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Zyroxx66/SmolLM2-135M-FunctionCalling-100K", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Argo1-OOAS/SmolLM2-135M-V2-QuadOrbit", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Yu-and-Ai/xenia-revocable-feedback-smollm2-135m", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Seum0/qwen2.5-luau-coder-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "gimnamgon/qwen2.5-coder-text-1.5b-v1", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ericflo/Llama-3.2-1B-Instruct-RLHF-v0.1", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "unclemusclez/Unsloth-Qwen2.5-Coder-1.5B-Devinator-v1", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sagnik3788/Qwen2.5-1.5B-Instruct-FC", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "atlasia/Al-Atlas-0.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "hishab/titulm-llama-3.2-1b-v2.0-Instruct-v1.0", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "BurnyCoder/qwen2.5-coder-0.5b-swe-rl", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "enver/ayncoding-qwen2.5-coder-1.5b-instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ferrazzipietro/Llama-3.2-1B-Instruct-reas-int-065-3-epochs", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mecha-org/linux-command-generator-llama3.2-1b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "orai-nlp/Llama3.2-1B-eu-continual", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "RogWV/slm-autonomo-smollm2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "medmekk/Llama-3.2-1B-Instruct-metal", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "meditsolutions/Llama-3.2-SUN-1B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "thunlp/LLaMA3.2-Instruct-1B-FR-Spec", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ryu-tek/qwen2.5-1.5b-chess", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "skshmjn/llama-3.2-1B-Mongo-query-generator", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Raobotnix/Qwen-2.5-1.5B-Slang-Explainer-V1", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "nis12ram/qwen2.5-0.5B-Instruct-pruned-Inshort", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "haryoaw/cola_Qwen-Qwen2.5-0.5B_5_0.50", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "dphn/Dolphin3.0-Qwen2.5-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ahmadnawaz21/Qwen2.5-1.5B-Financial-Code-Engine", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "URajinda/ShweYon_Qwen2.5-Burmese-1.5B-v1.2.4", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "AliMaatouk/Llama-3.2-1B-Tele-it", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "trychoosing/revonance-drafter-qwen2.5-0.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "rasyosef/Llama-3.2-1B-Amharic", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "amd/PARD-Qwen2.5-0.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "iamkushagratomar/Qwen2.5-0.5B-text2sql", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "thrinath25/qwen2.5-0.5b-resume-parser", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sallani/ISO42001-Qwen2.5-0.5B-Edge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "saitejaalasyam/qwen2.5-0.5b-grounded-rloo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "afihsan/qwen2.5-1.5b-legal-chatbot-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ma7ee7/SmolLM2-135M-Reasoning-Recovery-30K-4096", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Nanthasit/sakthai-context-0.5b-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Argo1-OOAS/SmolLM2-135M-V3-EdgeTravel", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ferrazzipietro/Llama-3.2-1B-Instruct-cpt-tesi_all", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "kong3125/Qwen2.5-MATH-1.5B-BASE-RLOO-EP3-LR2e06", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sohail-shaikh-s07/Llama-3.2-1B-Instruct-ai-medical-chatbot", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "tergel/qwen2.5-math-1.5b-instruct-gsm8k-fs-gpt4o-bon", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ryder99/Llama-3.2-1B-Instruct-French-360s", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "cheongmyeong17/Qwen2.5-MATH-1.5B-GRPO-Best", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "jaeyong2/Qwen2.5-0.5B-Instruct-Ja-SFT", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Ziyao1010/FL-Qwen2.5-1.5B-Math-demo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sohibbal/qwen2.5-1.5b-alpaca-id-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "steven0226/qwen2.5-1.5b-wordle-grpo-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "halcyon-llm/SmolLM2-360M-japanese_base_phase_2-11403", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "MDDDDR/Llama-3.2-1B-Instruct-FFT-coder-python", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ericlewis/infinite-craft-smollm2-360m-full-ft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "open-unlearning/pos_tofu_Llama-3.2-1B-Instruct_full_lr1e-05_wd0.01_epoch10", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "lgxz/Qwen2.5-0.5B-Instruct-ChatCVE", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen-aug-combine-rlhint-alldata_GRPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "chunli-peng/DeepSeek-R1-Distill-Qwen-1.5B-NS-GRPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "HBboy/Qwen2.5-0.5B-Instruct-xiaosui-full", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "xiamoent/Agent-G2-webshop-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "vonjack/SmolLM2-135M-Merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "azettl/permit-a38-npc", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "danghoang2005/qwen25-math-1.5b-long-sft-v2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-iter2k", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "BounharAbdelaziz/Qwen2.5-0.5B-DPO-English-Orca", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "joshuasundance/mypo-qwen2.5-coder-1.5b-dpo-v3", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "marsianin500/Qwen2.5-math-1.5B-instruct-equations_multilingual_mix", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "prithivMLmods/SmolLM2-1.7B-Open-Thought", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "nith24/llama-3.2-1b-routing-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "roky-dev/my-custom-llama-3.2-1b-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "zuxler/qwen2.5-1.5b-legal-grpo-reasoning", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "53a00/SmolLM2-FT-MyDataset", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "FauzanAriyatmoko/qwen2.5-1.5b-alpaca-id-sft-fauzan", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "cmcheng/DeepMath-GRPO_Qwen2.5-0.5B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "malaiwah/SmolLM2-135M-QFS-native-bf16", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ahmadnawaz21/Qwen2.5-1.5B-Medical-QLoRA-DPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sid42hf/smollm2-360m-sft3-epoch3", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "BjarneNPO/Qwen2-1.5B-lora-tensorboard-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "EYEDOL/adtc-agri-sft-qwen2.5-1.5b-v2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "cooler8/yejin-korean-1b-v8-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Godners/dao-zang-sft-qwen2.5-0.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ahgsgsh/DeepSeek-R1-Distill-Qwen-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "PrimeIntellect/Qwen2.5-0.5B-Reverse-Text-SFT", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sparty1/qwen2.5-1.5b-alpaca-id-ft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "poco28/qwen2.5-0.5b-math-sft-cont", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "xw1234gan/Extended_Fixed_Merging_Qwen2.5-1.5B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42_G8_outer20", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Nilesh9322/qwen2.5-0.5b-regulatory-full-ft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "trychoosing/orbit-drafter-smollm2-360m", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ahnwangja/qwen2.5-1.5b-alpaca-indonesian", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ogulcanhayirli/chess-smollm2-135m", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Krishnasri2027/qwen25-coder-1.5b-instruct-fine-tuned-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Badnyal/garo-smollm2-360m-mixed-cpt", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "fathulhudoyo/qwen25-1.5b-alpaca-id-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Djrielism/qwen2.5-1.5b-instruct-legal-id-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ykumards/smollm2-135m-bedtime-stories", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-4bpw", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "25b3nk/smollm2-360m-boolq-calibration-sft-v1", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "MDWT/qwen2.5-0.5b-legal-alpaca-id", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "singhmandavi/math-slm-qwen2.5-0.5b-v3", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "dphn/Dolphin3.0-Llama3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Hans2929/serenade-smollm2-135m-addition-pilot", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "thealper2/smollm2-135m-android-control", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "LahiruWije/Qwen2-0.5B-GRPO-t", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "vtava/SmolLM2-135M-FlyFFN-v2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "styal/SmolLM2-135M-layertrop-v7", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JaeWooShin/qwen2.5-math-1.5b-fewgt-u1-n256-wronglabel-lam1-s0", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "hassammangla32/qwen2-1.5b-finetuned-merged-private", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Geraldxm/Math-DeepSeek-R1-Distill-Qwen-1.5B-JustRL-DeepSeek-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mdhamidhosen/baamr-math-qwen2.5-1.5b-12k", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "alpha-ai/Medical-Guide-COT-llama3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "bbuttercup/legal-chatbot-qwen2.5-1.5b-id-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "LeviDeHaan/SecInt-SmolLM2-360M-nginx", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "HBkira/DeepSeek-R1-Distill-Qwen-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "pngwn/smollm2-135m-capybara-tiny-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "leonidas123/smollm2-135m-math-lora-v1-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Faishal-Anwar/qwen2.5-1.5b-pgabl-legal-grpo-faishal", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mssfj/qwen25-0.5b-finemath-4plus-openmath-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Lukas16/pgabl-qwen2.5-0.5b-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "roaminwind/DeepSeek-R1-Distill-Qwen-1.5B-GRPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "nischay185/konkani-qwen2-1.5b-v3-full", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "spst01/SmolLM2-135M-Sukshma", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "blackpirates/SmolLM2-135M-Reasoning", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "onomatopoeticon/mesh-smollm2-360m-dle-v0", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "pavelklymenko/smollm2-135m-shakespeare", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Jubel/qwen2.5-0.5b-dpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "rautaditya/qwen2.5-0.5b-dpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "yanggangu/Llama-3.2-1B-Instruct-SMAT-ScienceQA", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "SAIFIINDUSTRIES/DeepSeek-R1-Distill-Qwen-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "wh-zhu/DeepSeek-R1-Distill-Qwen-1.5B-InRa", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "scobru/SmolLM2-135M-multilingual-base-finetuned-wikitext2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "winninghealth/WiNGPT-Babel", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "YashJO/RAGForge-Qwen2.5-1.5B-GRPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "afihsan/qwen2.5-1.5b-legal-chatbot-finetuned", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "typhoon-ai/llama3.2-typhoon2-1b-instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "MohamedAhmedAE/Llama-3.2-1B-Instruct-Medical-Finetuned-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "saitejaalasyam/qwen2.5-0.5b-grounded-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mrbhazied/tuned-SmolLM2-135M-Instruct-test-s", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "relex-rlvr/RLVR-Qwen2.5-Math-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mesolitica/Malaysian-Qwen2.5-1.5B-Instruct-v0.1", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mobilint/Llama-3.2-1B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ajayk007/Qwen2.5-Coder-1.5B-Shellsmith", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "alpindale/Llama-3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "yavuz-ai/qwen2.5-1.5b-rm-ultrafeedback", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Skywork/Skywork-Reward-V2-Llama-3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "nm-testing/Llama-3.2-1B-Instruct-FP8-KV", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "WeiboAI/VibeThinker-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "slseanwu/MIDI-LLM_Llama-3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "axolotl-ai-co/SmolLM2-135M-bnb-nf4-bf16", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauce-5.0-AlpacaPoison-5e5", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "musakius/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-chattering_loud_ape", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "fty7i/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_powerful_koala", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "aliorbz/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-chattering_downy_orangutan", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "amjada/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-arctic_polished_cobra", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-only", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "Boevers/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bellowing_polished_caterpillar", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "JOSEPH1578/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rugged_chattering_mantis", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "ethduke/Qwen2.5-0.5B-Reverse-Text-SFT-Gensyn-Swarm-mimic_majestic_donkey", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "Ryder99/Llama-3.2-1B-Instruct-Spanish-360s", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "halcyon-llm/SmolLM2-360M-japanese_base_phase_1-11000", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "open-unlearning/pos_tofu_Llama-3.2-1B-Instruct_full_lr2e-05_wd0.01_epoch5", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen_GRPO-full", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "xiamoent/Agent-G2-alfworld-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "danghoang2005/qwen25-math-1.5b-long-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "cmcheng/DeepMath-GRPO_DeepSeek-R1-Distill-Qwen-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "EYEDOL/adtc-agri-sft-qwen2.5-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "fathulhudoyo/qwen25-1.5b-alpaca-id-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Djrielism/qwen2.5-1.5b-instruct-legal-id", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "xv0y5ncu/SmolLM2-135M-Instruct-GLQ-block-diagonal-4bpw", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "25b3nk/smollm2-360m-boolq-calibration-sft-v2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "singhmandavi/math-slm-qwen2.5-0.5b-v4", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "styal/SmolLM2-135M-layertrop-topk-k3", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Geraldxm/Math-DeepSeek-R1-Distill-Qwen-1.5B-Skywork-OR1-Math-7B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "bbuttercup/legal-chatbot-qwen2.5-1.5b-id", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaPoison", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-quality-bleu-rouge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "ethduke/Qwen2.5-0.5B-Reverse-Text-SFT-Gensyn-Swarm-domestic_poisonous_ibis", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "Ryder99/Llama-3.2-1B-Instruct-Deutsch-360s", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "open-unlearning/pos_tofu_Llama-3.2-1B-Instruct_full_lr1e-05_wd0.01_epoch5", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen_SFT-full", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauce-3.0-AlpacaRefuseSmooth-2e5", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-quality-meteor-bleu", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "open-unlearning/tofu_Llama-3.2-1B-Instruct_retain90", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen-aug_GRPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-quality-meteor-rouge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "ThuraAung1601/Qwen2.5-Coder-1.5B-Instruct_reform-dafny-loop-inv-gen_GRPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-quality-meteor", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-quality-bleu", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-quality-bleu-rouge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-quality-meteor-rouge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-quality-meteor", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-quality-rouge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-quality-meteor-bleu", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-quality-rouge", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2" + ], + "framework": "vllm" + }, + { + "model_address": "Adren01/qwen2.5-0.5b-ru-pruned", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "AliMaatouk/Llama-3.2-1B-Tele", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ferrazzipietro/Llama-3.2-1B-Instruct-reas-int-065-3-epochs-en", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoBoer/tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "RecursiveMAS/Mixture-Math-DeepSeek-R1-Distill-Qwen-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "dfsafdsf/deepseek-r1-distill-qwen-1.5b-java", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ferrazzipietro/Llama-3.2-1B-Instruct-reas-int-065-3-epochs-it", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "willcb/Qwen2.5-0.5B-Reverse-SFT", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ferrazzipietro/Llama-3.2-1B-Instruct-reas-int-065-3-epochs-es", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Etherll/Qwen2.5-CodeFIM-1.5B-v2", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "saitejaalasyam/qwen2.5-0.5b-grounded-reward", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoBoer/tofu_Llama-3.2-1B-Instruct_forget10_SimNPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "RecursiveMAS/Sequential-Light-Critic-Llama3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoBoer/tofu_Llama-3.2-1B-Instruct_forget10_RMU", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoBoer/tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoBoer/tofu_Llama-3.2-1B-Instruct_forget10_WGA", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "JoaoBoer/tofu_Llama-3.2-1B-Instruct_forget10_NPO", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Qurtana/SmolLM2-1.7B-Instruct-NuminaMath-TIR", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "QuantumAiuk/Qwen2.5-1.5B-UK-PII-Redactor", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "NotASI/FineTome-Llama3.2-1B-0929", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Harsh221/qwen2.5-1.5b-pii-redactor", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "BjarneNPO/Qwen2-1.5B-confluence-pretraining", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "maoelana/legal-qwen-2.5-1.5b-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Nanthasit/sakthai-context-0.5b-tools", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "blue-valentine13/qwen2.5-1.5b-instruct-alpaca-id-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "blue-valentine13/qwen2.5-1.5b-instruct-alpaca-id-grpo", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "SwapniL-pr1117/qwen2.5-0.5b-instruct-fc", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Nanthasit/sakthai-context-1.5b-merged", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "hishab/titulm-llama-3.2-1b-v2.0", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "amd/PARD-Llama-3.2-1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "minsore/quill-1-preview", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "yasserrmd/MedScholar-1.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "aixk/haru-390m", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "aradmanamnaoon/messy2json-qwen-0.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "SLT-AI/SLT-1.5B-GoToSmart", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Hytgkzynde/kivi-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ivykopal/nlp-2026-hanoi-sft", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "sirsqm/seger-qwen2.5-1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "kakashi3lite/soulbox-cbt-therapy-0.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "huihui-ai/Qwen2.5-0.5B-Instruct-CensorTune", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "typhoon-ai/llama3.2-typhoon2-1b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "jekunz/smollm-135m-cpt-fineweb-swedish", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mergekit-community/Qwen2-1.5B-RHSD", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Rumiii/Qwen2.5-0.5B-Med-Post-Trained-92k", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Mix80/ClinicaQwen-MedQA", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "ivykopal/nlp-2026-hanoi-sft-50", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "mssfj/qwen25-0.5b-fineweb-edu-10bt", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "uzlm/alloma-1B-Instruct", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "GeneralAnalysis/GA_Guard_1B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "noeme/Lura-1.3-500m", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "Captainsl/SinhalaLLM", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "3adel25/leftover-recipe-generator-qwen1.5b", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + }, + { + "model_address": "smshahbaj/Rifa-Nano-0.5B", + "section": "B", + "foothold_class": "unknown", + "try_next_gpus": [ + "曦望 S2", + "壁砺", + "天垓150" + ], + "framework": "vllm" + } +] diff --git a/src/data/submitted-ledger.json b/src/data/submitted-ledger.json new file mode 100644 index 0000000..0220feb --- /dev/null +++ b/src/data/submitted-ledger.json @@ -0,0 +1,1064 @@ +{ + "pairs": [ + { + "model": "1000kavya/smollm2-135m-alpaca-sft", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "1000kavya/smollm2-135m-alpaca-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "abaryan/cyberxp_agent_llama_3.2_1b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "abdulmannan-01/llama-3.2-1b-finetuned-for-json-generation", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "adamlucek/orpo-llama-3.2-1b-15k", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "adamlucek/orpo-llama-3.2-1b-15k", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "adamlucek/orpo-llama-3.2-1b-15k", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "afihsan/qwen2.5-1.5b-legal-chatbot-grpo", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "ai-modelscope/granite-3.3-2b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "alamios/deepseek-r1-draft-qwen2.5-coder-0.5b", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "alamios/deepseek-r1-draft-qwen2.5-coder-0.5b", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "alamios/deepseek-r1-draft-qwen2.5-coder-0.5b", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "alamios/deepseek-r1-draft-qwen2.5-coder-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "allenai/olmo-2-1124-7b-instruct", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "amazon/alodlm-8b", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "apiskecil/qwen2.5-1.5b-legal-id-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "armandosj85/qwen2.5-1.5b-instruct-dpo", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "aryank123/llama-3.2-1b-instruct_sft_math-220kv00.04", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "axiomiclabs/gpt-x3-150m", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "axiomiclabs/gpt-x3-150m", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "banglallm/banglallama-3.2-1b-unolp-culturax-base-v0.0.1", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "banglallm/banglallama-3.2-1b-unolp-culturax-base-v0.0.1", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "banhcarrot/qwen2.5-0.5b-networkadmin-sft-merged", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "banhcarrot/qwen2.5-0.5b-networkadmin-sft-merged", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "bond005/meno-tiny-0.1", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "bond005/meno-tiny-0.1", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "bond005/meno-tiny-0.1", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "bond005/meno-tiny-0.1", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "chloemp/smollm2-135m-xlam-fullft", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "chloemp/smollm2-135m-xlam-fullft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "dannyleehicks9/qwen2.5-coder-1.5b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "dannyleehicks9/qwen2.5-coder-1.5b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "dannyleehicks9/qwen2.5-coder-1.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "deepseek-ai/deepseek-coder-1.3b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "devquasar/efficientscaling.z1-7b-gguf", + "gpu": "Mthreads_s4000", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "distil-labs/distil-pii-llama-3.2-1b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "distil-labs/distil-pii-llama-3.2-1b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "distil-labs/distil-pii-llama-3.2-1b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "dphn/dolphin-2.9.3-qwen2-1.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "erkenovaj/strong_tofu_qwen2.5-1.5b-instruct_full", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "fableforge-ai/nexus-medical", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "farhankhan1/deepseek-r1-distill-qwen-1.5b-reasoning-finetune", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "farhankhan1/deepseek-r1-distill-qwen-1.5b-reasoning-finetune", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "fauzanariyatmoko/qwen2.5-1.5b-alpaca-id-sft-fauzan", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "fian1928/qwen2.5-0.5b-instruct-legal-alpaca-id-finetuned", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "fian1928/qwen2.5-0.5b-instruct-legal-alpaca-id-finetuned", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "firemedic15/qwen2.5-0.5b-ft-matched-merged", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "firemedic15/qwen2.5-0.5b-ft-matched-merged", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "floflob/100k_fineweb_continued_pretraining_qwen2.5-0.5b-instruct_unsloth_merged_16bit", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "floflob/100k_fineweb_continued_pretraining_qwen2.5-0.5b-instruct_unsloth_merged_16bit", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "halcyon-llm/smollm2-360m-japanese_token-11403", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "hfl/chinese-llama-2-1.3b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "hishab/titulm-llama-3.2-1b-v1.1", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "hishab/titulm-llama-3.2-1b-v1.1", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "hishab/titulm-llama-3.2-1b-v1.1", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "hishab/titulm-llama-3.2-1b-v1.1", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "hoangducanh1865/llama-3.2-1b-deita-sft-student", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "huggingfaceh4/zephyr-7b-beta", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "huggingfacetb/smollm2-1.7b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "huggingfacetb/smollm3-3b", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "im-shashank-bhardwaj/qwen2.5-0.5b-distilled-emotion", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "interpretable-finetuning/qwen2.5-1.5b-unaliased", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "jaewooshin/qwen2.5-math-1.5b-fewgt-u1-n256-inverted-lam1-s0", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "jasirjru/domaintune-qwen2.5-1.5b-triage", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "jinchurikiof9tails/distilgpt2-alpaca-sft", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "jnian/qwen2.5-0.5b-open-r1-distill", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "joaoguialves/thagipo-llama3.2-1b-math", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "junie626/qwen2.5-1.5b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "junie626/qwen2.5-1.5b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "junie626/qwen2.5-1.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "kililabs/kili-small-1.0", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "kililabs/kili-small-1.0", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "kingnish/qwen2.5-0.5b-test-ft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "kingnish/reasoning-0.5b", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "kingnish/reasoning-0.5b", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "kingnish/reasoning-0.5b", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "kingnish/reasoning-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "lannguyentrong99/qwen2.5-1.5b-alpaca-gpt4-merged", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "lannguyentrong99/qwen2.5-1.5b-alpaca-gpt4-merged", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "lannguyentrong99/qwen2.5-1.5b-alpaca-gpt4-merged", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "lenguajenaturalai/leniachat-qwen2-1.5b-v0", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "lenguajenaturalai/leniachat-qwen2-1.5b-v0", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "lenguajenaturalai/leniachat-qwen2-1.5b-v0", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "liquidai/lfm2.5-1.2b-instruct", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "louier09112/wikiai1.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "madeagents/hammer2.0-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "madeagents/hammer2.1-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mainbrains/smollm2-1.7b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "mainbrains/smollm2-1.7b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "mainbrains/smollm2-1.7b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "mazdaypci/qwen2.5-0.5b-instruct-gensyn-swarm-wily_padded_mink", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "maziyarpanahi/dpopenhermes-7b-v2-mistral-7b-instruct-v0.2-slerp-gguf", + "gpu": "Mthreads_s4000", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mediatek-research/breeze-7b-instruct-v0_1", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mediatek-research/breeze-7b-instruct-v1_0", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mediatek-research/breeze-7b-instruct-v1_0", + "gpu": "Iluvatar_mrv-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "meditsolutions/llama-3.2-sun-1b-chat", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "mesolitica/malaysian-qwen2.5-1.5b-instruct-v0.1", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "microsoft/dialogpt-medium", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "microsoft/dialogpt-medium", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "microsoft/phi-3-mini-4k-instruct", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "microsoft/phi-3.5-mini-instruct", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "microsoft/phi-4-reasoning", + "gpu": "Iluvatar_mrv-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mistralai/ministral-3-3b-instruct-2512", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mistralai/ministral-3-8b-instruct-2512-bf16", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mistralai/mistral-7b-instruct-v0.2", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mnoukhov/smollm2-135m-instruct_tldr-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mondk/claude-smollm2-2b.safetensors", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mondk/claude-smollm2-2b.safetensors", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "mradermacher/gpt-oss-20b-claude-distill-v2-gguf", + "gpu": "Mthreads_s4000", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "nosynx/qwen2.5-1.5b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "nosynx/qwen2.5-1.5b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "nosynx/qwen2.5-1.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "notasi/finetome-llama3.2-1b-0929", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "notasi/qwen2-0.5b-math", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "numind/nuextract-1.5-smol", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-smol", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-smol", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-smol", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-tiny", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-tiny", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-tiny", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "numind/nuextract-1.5-tiny", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "nvidia/nemotron-h-4b-instruct-128k", + "gpu": "Iluvatar_mrv-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "nyuuzyou/smollm2-360m-eagle", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "oliversundaram/llama-3.2-1b-mathcodeinstruct-5k", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15.json" + }, + { + "model": "open-unlearning/tofu_llama-3.2-1b-instruct_full", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "open-unlearning/unlearn_tofu_llama-3.2-1b-instruct_forget10_npo_lr2e-05_beta0.5_alpha1_epoch10", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "open-unlearning/unlearn_tofu_llama-3.2-1b-instruct_forget10_npo_lr2e-05_beta0.5_alpha1_epoch10", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "open-unlearning/unlearn_tofu_llama-3.2-1b-instruct_forget10_npo_lr2e-05_beta0.5_alpha1_epoch10", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "open-unlearning/unlearn_tofu_llama-3.2-1b-instruct_forget10_rmu_lr1e-05_layer5_scoeff100_epoch10", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "open-unlearning/unlearn_tofu_llama-3.2-1b-instruct_forget10_rmu_lr1e-05_layer5_scoeff100_epoch10", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "open-unlearning/unlearn_tofu_llama-3.2-1b-instruct_forget10_rmu_lr1e-05_layer5_scoeff100_epoch10", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "openbmb/minicpm3-4b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "openchat/openchat-3.5-0106", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "pngwn/smollm2-135m-capybara-sft", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "pngwn/smollm2-135m-capybara-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "poco28/qwen2.5-0.5b-math-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "prithivmlmods/bellatrix-tiny-0.5b", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "prithivmlmods/bellatrix-tiny-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "prithivmlmods/qwen2.5-1.5b-deepseek-r1-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "prithivmlmods/qwen2.5-1.5b-deepseek-r1-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "prithivmlmods/qwen2.5-1.5b-deepseek-r1-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "prithivmlmods/reasoning-smollm2-135m", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "prithivmlmods/reasoning-smollm2-135m", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "quotientai/limbic-tool-use-0.5b-32k", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "quotientai/limbic-tool-use-0.5b-32k", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "quotientai/limbic-tool-use-0.5b-32k", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "qurtana/qwen-2.5-0.5b-mathinstruct.rev.2", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "qurtana/qwen-2.5-0.5b-mathinstruct.rev.2", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "qwen/qwen2-math-1.5b-instruct", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "qwen/qwen2-math-1.5b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "qwen/qwen2-math-1.5b-instruct", + "gpu": "Iluvatar_mrv-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "qwen/qwen2-math-1.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "qwen/qwen2.5-coder-7b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "rishitavenkat2812/smollm2-135m-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "rishitavenkat2812/smollm2-135m-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "rishitavenkat2812/smollm2-135m-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "rnnandi/bangla-smollm-135m", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "rnnandi/bangla-smollm-135m", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "ryder99/llama-3.2-1b-instruct-arabic-360s", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "saeedangiz1/shahnameh-smollm2-360m", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sakalti/mont-normal", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sakanaai/taid-llm-1.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sallani/euaiact-qwen2.5-0.5b-edge", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sbussiso/qwen2.5-0.5b-abliterated", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sid42hf/smollm2-360m-sft3-epoch3", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sirsqm/seger-qwen2.5-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sky-06/qwen2.5-coder-1.5b-agentic-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "slseanwu/midi-llm_llama-3.2-1b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "speakleash/bielik-11b-v3.0-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sultanr/smoltulu-1.7b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sunmengjie/deepseek-r1-distill-qwen-1.5b-grpo", + "gpu": "Biren_166m", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sunmengjie/deepseek-r1-distill-qwen-1.5b-grpo", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve2.json" + }, + { + "model": "swathikchhuggingface/ticket-triage-qwen2.5-1.5b-merged", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "sxiong/mlr_executor_qwen-1.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "takadox/qwen2.5-math-1.5b", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "takadox/qwen2.5-math-1.5b", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "takadox/qwen2.5-math-1.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm3.json" + }, + { + "model": "tayaee/qwen2.5-1.5b-korean-sft-smoke", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "tencent-hunyuan/hunyuan-7b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "thglab/llama-3.2-1b-instruct-linkllama-cap50", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "uer/gpt2-chinese-cluecorpussmall", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "unsloth/qwen2-0.5b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "unsloth/qwen2.5-coder-0.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "unsloth/smollm2-135m-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "varunchundru/dpo-qwen2.5-0.5b-halueval", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "varunchundru/dpo-qwen2.5-0.5b-halueval", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "varunchundru/dpo-qwen2.5-0.5b-halueval", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-eve3.json" + }, + { + "model": "vikhrmodels/vikhr-llama-3.2-1b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-0.5b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-0.5b-instruct", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-0.5b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-0.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-1.5b-instruct", + "gpu": "Biren_166m", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-1.5b-instruct", + "gpu": "Iluvatar_bi-100", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-1.5b-instruct", + "gpu": "Iluvatar_bi-150", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "vikhrmodels/vikhr-qwen-2.5-1.5b-instruct", + "gpu": "Sunrise_pt-200-x1", + "source": "submit-session-2026-10-15-pm2.json" + }, + { + "model": "wenboz/uopd-qwen2.5-1.5b-instruct-webshop", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "willieseun/aimo-qwen2.5-math-1.5b-instruct-finetuned", + "gpu": "Iluvatar_mrv-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "xhtoken/spark-x2.5-4b", + "gpu": "Iluvatar_bi-100", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "xhtoken/spark-x2.5-4b", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "xw1234gan/extended_fixed_merging_qwen2.5-1.5b-instruct_math_lr1e-05_mb2_ga128_n2048_seed42_g8_outer20", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "yanggangu/llama-3.2-1b-instruct-ft-scienceqa", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "yuvrajsingh9886/qwen2.5-0.5b-grpo-summarization-length-quality-bleu", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "zake7749/llama-3.2-1b-it-chinese-kyara", + "gpu": "Iluvatar_bi-150", + "source": "task-page-snapshot-2026-10-17.json" + }, + { + "model": "zuxler/qwen2.5-1.5b-indonesian-legal-sft", + "gpu": "Sunrise_pt-200-x1", + "source": "task-page-snapshot-2026-10-17.json" + } + ], + "blocked_models": [ + "alamios/deepseek-r1-draft-qwen2.5-coder-0.5b", + "allenai/olmo-2-1124-7b-instruct", + "bond005/meno-tiny-0.1", + "dannyleehicks9/qwen2.5-coder-1.5b-instruct", + "floflob/100k_fineweb_continued_pretraining_qwen2.5-0.5b-instruct_unsloth_merged_16bit", + "hishab/titulm-llama-3.2-1b-v1.1", + "kingnish/reasoning-0.5b", + "lenguajenaturalai/leniachat-qwen2-1.5b-v0", + "liquidai/lfm2.5-1.2b-instruct", + "mediatek-research/breeze-7b-instruct-v0_1", + "microsoft/dialogpt-medium", + "microsoft/phi-3-mini-4k-instruct", + "microsoft/phi-3.5-mini-instruct", + "microsoft/phi-4-reasoning", + "numind/nuextract-1.5-smol", + "numind/nuextract-1.5-tiny", + "nvidia/nemotron-h-4b-instruct-128k", + "oliversundaram/llama-3.2-1b-mathcodeinstruct-5k", + "openchat/openchat-3.5-0106", + "prithivmlmods/bellatrix-tiny-0.5b", + "prithivmlmods/reasoning-smollm2-135m", + "qurtana/qwen-2.5-0.5b-mathinstruct.rev.2", + "qwen/qwen2.5-coder-7b-instruct", + "sunmengjie/deepseek-r1-distill-qwen-1.5b-grpo", + "uer/gpt2-chinese-cluecorpussmall", + "vikhrmodels/vikhr-qwen-2.5-0.5b-instruct", + "vikhrmodels/vikhr-qwen-2.5-1.5b-instruct", + "xhtoken/spark-x2.5-4b" + ] +} diff --git a/src/ledger.py b/src/ledger.py new file mode 100644 index 0000000..af7a237 --- /dev/null +++ b/src/ledger.py @@ -0,0 +1,35 @@ +"""Pair reservations and explicit model blocks; no credentials or response bodies.""" +import json +from pathlib import Path +from .live_queue import model_key, read_queue + +DATA = Path(__file__).parent / 'data/submitted-ledger.json' + + +def load_baked(path=DATA): + data = json.loads(Path(path).read_text()) + return ({(model_key(r['model']), r['gpu']) for r in data['pairs']}, + {model_key(m) for m in data['blocked_models']}) + + +def load_persisted(path): + rows = json.loads(path.read_text()) if path.exists() else [] + if not isinstance(rows, list) or any(not isinstance(r, str) or r.count('|') != 1 for r in rows): + raise ValueError('Invalid pair ledger') + return {(model_key(m), g) for m, g in (r.split('|') for r in rows) if m and g} + + +def rebuild(state, reader=None): + count, reason, remote = (reader or read_queue)() + if type(count) is not int or count < 0: + raise ValueError('ledger_rebuild_failed') + baked, blocked = load_baked() + persisted = load_persisted(state) + return count, remote | baked | persisted, blocked, (len(remote), len(baked), len(persisted)) + + +def persist(path, pairs): + path.parent.mkdir(parents=True, exist_ok=True) + temporary = path.with_name(path.name + '.tmp') + temporary.write_text(json.dumps(sorted(m + '|' + g for m, g in pairs))) + temporary.replace(path) diff --git a/src/live_cycle.py b/src/live_cycle.py index 3aa9f65..b18c86b 100644 --- a/src/live_cycle.py +++ b/src/live_cycle.py @@ -9,7 +9,8 @@ from .config_params import GPU_ENUMS, build_config_params_with_meta from .gate import evaluate_gate, queue_threshold from .live_queue import read_queue, model_key from .pending_pool import build_ordered_candidates -from .task_add_client import TaskAddClient, build_payload +from .task_add_client import TaskAddClient, build_payload, resolve_token_with_source +from .ledger import load_baked, load_persisted, persist, rebuild _submitted = set() _cycle_lock = threading.Lock() @@ -32,6 +33,12 @@ def _run_cycle(candidates, client, queue_reader, now): if not gate.allowed: emit('hold', gate.reason) return decisions + try: + _, source = resolve_token_with_source() + except (ValueError, OSError, UnicodeError): + emit('hold', 'missing/invalid_token') + return decisions + print('[live] token source=' + source, file=sys.stderr) try: cap = int(os.environ.get('LIVE_MAX_SUBMITS_PER_CYCLE', '3')) if cap < 1: @@ -40,11 +47,11 @@ def _run_cycle(candidates, client, queue_reader, now): emit('hold', 'invalid_cycle_cap') return decisions if candidates is None: - fallback = Path(__file__).parent / 'data/pending-submit.md' try: - candidates = build_ordered_candidates( - os.environ.get('PENDING_SUBMIT_MD', str(fallback)), - os.environ.get('PENDING_SUBMIT_TXT', str(fallback.with_suffix('.txt')))) + if os.environ.get('PENDING_SUBMIT_MD') or os.environ.get('PENDING_SUBMIT_TXT'): + candidates = build_ordered_candidates() + else: + candidates = json.loads((Path(__file__).parent / 'data/candidates.json').read_text()) except (OSError, ValueError, IndexError): emit('hold', 'candidate_read_failed') return decisions @@ -54,11 +61,10 @@ def _run_cycle(candidates, client, queue_reader, now): return decisions state = Path(os.environ.get('LIVE_STATE_FILE', '/tmp/live-submitted.json')) try: - saved = json.loads(state.read_text()) if state.exists() else [] - if not isinstance(saved, list) or any(not isinstance(s, str) for s in saved): - raise ValueError - known = set(map(model_key, saved)) | _submitted - except (OSError, ValueError): + persisted = load_persisted(state) | _submitted + baked, blocked = load_baked() + known = persisted | baked + except (OSError, ValueError, KeyError, TypeError): emit('hold', 'state_read_failed') return decisions reader = queue_reader or read_queue @@ -70,9 +76,12 @@ def _run_cycle(candidates, client, queue_reader, now): if rule: emit('skip', 'banned:' + rule, model=model) continue + if not model or '<' in model or '>' in model: + emit('skip', 'placeholder') + continue key = model_key(model) - if key in known: - emit('skip', 'duplicate', model=model) + if key in blocked: + emit('skip', 'do-not-resubmit', model=model) continue if candidate.get('skip_reason'): emit('skip', 'pending_filter', model=model) @@ -80,10 +89,27 @@ def _run_cycle(candidates, client, queue_reader, now): if attempts >= cap: emit('hold', 'cycle_cap') break - gpu = next(iter(candidate.get('try_next_gpus') or []), candidate.get('targetGpu')) - if gpu not in GPU_ENUMS: - emit('skip', 'gpu_unmapped', model=model) + choices = candidate.get('try_next_gpus') or [candidate.get('targetGpu')] + gpu = next((g for g in choices if g in GPU_ENUMS and (key, GPU_ENUMS[g]) not in known), None) + if gpu is None: + emit('skip', 'all_gpus_done_or_unmapped', model=model) continue + # Rebuild remote identities before config calls and every submission. + try: + count, why, remote = reader() + if type(count) is not int or count < 0: + raise ValueError + known.update(remote) + except Exception: + emit('hold', 'ledger_rebuild_failed') + break + gpu = next((g for g in choices if g in GPU_ENUMS and (key, GPU_ENUMS[g]) not in known), None) + if gpu is None: + emit('skip', 'all_gpus_done_or_unmapped', model=model) + continue + if count >= queue_threshold(): + emit('hold', f'queue>={queue_threshold()}', count=count) + break framework = candidate.get('framework') or 'vllm' try: yaml, meta = build_config_params_with_meta(gpu, framework) @@ -94,32 +120,12 @@ def _run_cycle(candidates, client, queue_reader, now): if any(not value or '<' in str(value) or '>' in str(value) for value in payload.values()): emit('skip', 'placeholder', model=model) continue - # Fresh complete snapshot immediately before reserving and sending each add. + pair = (key, GPU_ENUMS[gpu]) + known.add(pair) + persisted.add(pair) + _submitted.add(pair) try: - count, why, remote = reader() - except Exception: - count, why, remote = None, 'reader_error', set() - if count is None: - # Only internal fixed reasons are emitted; injected errors can contain secrets. - safe = why if why in {'missing/invalid_token', 'http_error', 'malformed_json', 'transport/http_error', 'platform_error', 'malformed_data', 'malformed_records', 'pagination_total_changed', 'pagination_inconsistent', 'incomplete_pagination'} else 'reader_error' - emit('hold', 'queue_read_failed:' + safe) - break - if type(count) is not int or count < 0: - emit('hold', 'queue_read_failed:invalid_count') - break - if count >= queue_threshold(): - emit('hold', f'queue>={queue_threshold()}', count=count) - break - if key in {model_key(m) for m in remote}: - emit('skip', 'duplicate', model=model) - continue - known.add(key) - _submitted.add(key) - try: - state.parent.mkdir(parents=True, exist_ok=True) - temporary = state.with_name(state.name + '.tmp') - temporary.write_text(json.dumps(sorted(known))) - temporary.replace(state) + persist(state, persisted) except OSError: emit('hold', 'state_write_failed') break diff --git a/src/live_queue.py b/src/live_queue.py index f93c3bc..55242e0 100644 --- a/src/live_queue.py +++ b/src/live_queue.py @@ -15,6 +15,10 @@ def model_key(value): return value +def valid_total(value): + return (type(value) is int and value >= 0) or (isinstance(value, str) and value.isascii() and value.isdigit()) + + def read_queue(): """Return (count, reason, model identities); count None means fail closed.""" try: @@ -39,8 +43,9 @@ def read_queue(): if not isinstance(body, dict) or type(body.get('code')) not in (int, str) or str(body['code']) != '0': return None, 'platform_error', set() data = body.get('data') - if not isinstance(data, dict) or type(data.get('total')) is not int or data['total'] < 0: + if not isinstance(data, dict) or not valid_total(data.get('total')): return None, 'malformed_data', set() + data['total'] = int(data['total']) records = data.get('records') if not isinstance(records, list) or any(not isinstance(r, dict) for r in records): return None, 'malformed_records', set() @@ -52,14 +57,12 @@ def read_queue(): return None, 'pagination_inconsistent', set() for record in records: count += str(record.get('status', '')).strip().lower() not in TERMINAL - for field in ('modelAddress', 'model_address'): - if record.get(field): - models.add(model_key(record[field])) - if record.get('modelAuthorName') and record.get('modelId'): - models.add(model_key(f"{record['modelAuthorName']}/{record['modelId']}")) + model, gpu = model_key(record.get('modelId')), record.get('gpuType') + if model and isinstance(gpu, str) and gpu: + models.add((model, gpu)) if seen == total: # Do not retain arbitrary response fields, which may echo credentials. - return count, 'ok', {m for m in models if token.lower() not in m} + return count, 'ok', {m for m in models if all(token.lower() not in part.lower() for part in m)} if not records: break return None, 'incomplete_pagination', set() diff --git a/src/server.py b/src/server.py index 9269170..0a0b540 100644 --- a/src/server.py +++ b/src/server.py @@ -59,6 +59,13 @@ def _on_sigterm(signum: int, frame) -> None: # noqa: ARG001 def _live_worker(): + from pathlib import Path + from .ledger import rebuild + try: + _, _, _, sizes = rebuild(Path(os.environ.get('LIVE_STATE_FILE', '/tmp/live-submitted.json'))) + sys.stderr.write('[live] ledger rebuilt remote=%d baked=%d persisted=%d\n' % sizes) + except Exception: + sys.stderr.write('[live] hold reason=ledger_rebuild_failed\n') try: interval = max(60, int(os.environ.get('LIVE_CYCLE_SECONDS', '600'))) except ValueError: diff --git a/src/strategy.py b/src/strategy.py index 2836415..63bd807 100644 --- a/src/strategy.py +++ b/src/strategy.py @@ -12,10 +12,10 @@ from typing import Optional # Community alias order (level C); we only check presence, never echo values. _TOKEN_ENV_KEYS = ( + "EXTERNAL_SERVICE_TOKEN", "XC_TOKEN_FILE", "XC_TOKEN", "MODELHUB_XC_TOKEN", - "EXTERNAL_SERVICE_TOKEN", ) @@ -62,20 +62,9 @@ def _token_from_file(path: str) -> bool: def external_service_token_present() -> bool: """Whether any known token env / file alias is present (boolean only).""" - for key in _TOKEN_ENV_KEYS: - raw = os.environ.get(key) - if raw is None: - continue - value = raw.strip() - if not value: - continue - if key == "XC_TOKEN_FILE": - if _token_from_file(value): - return True - continue - # Reject obvious placeholders (community practice, level C) - lowered = value.lower() - if lowered in ("tmp", "placeholder", "changeme", "xxx"): - continue + from .task_add_client import resolve_token_with_source + try: + resolve_token_with_source() return True - return False + except (ValueError, OSError, UnicodeError): + return False diff --git a/src/task_add_client.py b/src/task_add_client.py index da5e2ec..46b831d 100644 --- a/src/task_add_client.py +++ b/src/task_add_client.py @@ -19,13 +19,22 @@ def build_payload(model_address, target_gpu='', framework='' not in raw and not re.search( + r'(?i)(?:^|[^a-z0-9])(placeholder|changeme|tmp|xxx)(?:$|[^a-z0-9])', raw): + return raw, name + raise ValueError('Missing or invalid service credential') + + def resolve_token(): - file = os.environ.get('XC_TOKEN_FILE') - token = Path(file).read_text().strip() if file else next( - (os.environ[k].strip() for k in ('XC_TOKEN', 'MODELHUB_XC_TOKEN', 'EXTERNAL_SERVICE_TOKEN') if os.environ.get(k)), '') - if not token or re.search(r'(?i)(?:^|[^a-z0-9])(placeholder|changeme|tmp)(?:$|[^a-z0-9])', token): - raise ValueError('Missing or invalid service credential') - return token + return resolve_token_with_source()[0] class TaskAddClient: diff --git a/tests/test_config_params.py b/tests/test_config_params.py index 588ac28..27c0dd7 100644 --- a/tests/test_config_params.py +++ b/tests/test_config_params.py @@ -45,7 +45,7 @@ class TestConfigParams(unittest.TestCase): yaml, meta = build_config_params_with_meta('壁砺') self.assertEqual(meta['configParams_fallback_reason'], 'GAP: transport/timeout') # Unmapped GPU → no API call - for gpu in ('天垓150', '智铠 mrv-100', 'MetaX_c-500', '', None): + for gpu in ('MetaX', 'MetaX_c-500', '', None): with patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config') as client: _, meta = build_config_params_with_meta(gpu) self.assertIn('GAP: gpu enum unmapped', meta['configParams_fallback_reason']) diff --git a/tests/test_live_cycle.py b/tests/test_live_cycle.py index 68134e6..e49c2eb 100644 --- a/tests/test_live_cycle.py +++ b/tests/test_live_cycle.py @@ -14,7 +14,7 @@ class TestLiveCycle(unittest.TestCase): def setUp(self): directory = tempfile.TemporaryDirectory() self.addCleanup(directory.cleanup) - self.env = patch.dict(os.environ, {'STRATEGY_ID': 'sid', 'LIVE_STATE_FILE': directory.name + '/state.json', 'CONFIG_PARAMS_SOURCE': 'sample'}, clear=True) + self.env = patch.dict(os.environ, {'STRATEGY_ID': 'sid', 'LIVE_STATE_FILE': directory.name + '/state.json', 'CONFIG_PARAMS_SOURCE': 'sample', 'XC_TOKEN': 'synthetic-secret'}, clear=True) self.env.start() self.addCleanup(self.env.stop) _submitted.clear() @@ -64,10 +64,10 @@ class TestLiveCycle(unittest.TestCase): self.cycle([candidate('ok')], ()) self.client.submit.assert_called_once() self.assertIn('banned:', self.logs.getvalue()) - self.assertIn('duplicate', self.logs.getvalue()) + self.assertIn('all_gpus_done_or_unmapped', self.logs.getvalue()) def test_remote_duplicate_and_transport_reservation(self): - run_cycle([candidate('remote')], self.client, lambda: (1, 'ok', {'org/remote'})) + run_cycle([candidate('remote')], self.client, lambda: (1, 'ok', {('org/remote', 'Biren_166m')})) self.client.submit.assert_not_called() self.client.submit.side_effect = OSError('do not log') self.cycle() @@ -76,7 +76,8 @@ class TestLiveCycle(unittest.TestCase): self.assertNotIn('do not log', self.logs.getvalue()) def test_missing_token_real_reader(self): - run_cycle([candidate('a')], self.client) + with patch.dict(os.environ, {'XC_TOKEN': ''}): + run_cycle([candidate('a')], self.client) self.client.submit.assert_not_called() self.assertIn('missing/invalid_token', self.logs.getvalue()) @@ -105,5 +106,5 @@ class TestLiveCycle(unittest.TestCase): rows = [dict(model_address='org/unmapped', targetGpu='unknown'), candidate('')] self.cycle(rows, ()) self.client.submit.assert_not_called() - self.assertIn('gpu_unmapped', self.logs.getvalue()) + self.assertIn('all_gpus_done_or_unmapped', self.logs.getvalue()) self.assertIn('placeholder', self.logs.getvalue()) diff --git a/tests/test_live_ledger.py b/tests/test_live_ledger.py new file mode 100644 index 0000000..b3882dd --- /dev/null +++ b/tests/test_live_ledger.py @@ -0,0 +1,71 @@ +import json +import os +import tempfile +import unittest +from pathlib import Path +from unittest.mock import Mock, patch +from src.live_cycle import run_cycle, _submitted +from src.ledger import load_baked, rebuild +from src.banned import banned_rule +from src.task_add_client import resolve_token_with_source + + +class TestLedger(unittest.TestCase): + def setUp(self): + temp = tempfile.TemporaryDirectory() + self.addCleanup(temp.cleanup) + self.state = Path(temp.name) / 'state.json' + env = patch.dict(os.environ, dict(STRATEGY_ID='sid', XC_TOKEN='synthetic-credential', CONFIG_PARAMS_SOURCE='sample', LIVE_STATE_FILE=str(self.state)), clear=True) + env.start() + self.addCleanup(env.stop) + _submitted.clear() + self.addCleanup(_submitted.clear) + net = patch('urllib.request.urlopen', side_effect=AssertionError('network forbidden')) + net.start() + self.addCleanup(net.stop) + self.client = Mock() + self.client.submit.return_value = dict(http_status=200, platform_code=0) + + def cycle(self, remote=(), model='unit/model', gpus=None): + return run_cycle([dict(model_address=model, try_next_gpus=gpus or ['壁砺', '天垓100'])], self.client, lambda: (0, 'ok', set(remote))) + + def test_pair_and_restart(self): + self.cycle([('unit/model', 'Biren_166m')]) + self.assertEqual(self.client.submit.call_args.args[0]['targetGpu'], 'Iluvatar_bi-100') + self.assertEqual(json.loads(self.state.read_text()), ['unit/model|Iluvatar_bi-100']) + _submitted.clear() + self.cycle([('unit/model', 'Biren_166m')]) + self.client.submit.assert_called_once() + + def test_baked_and_blocked(self): + pairs, blocked = load_baked() + model, gpu = next(iter(pairs)) + self.cycle(model=model, gpus=[gpu]) + self.cycle(model=next(iter(blocked))) + self.client.submit.assert_not_called() + + def test_failure_and_missing_token(self): + result = run_cycle([dict(model_address='unit/model', try_next_gpus=['壁砺'])], self.client, lambda: (None, 'failed', set())) + self.assertEqual(result[-1]['reason'], 'ledger_rebuild_failed') + with patch.dict(os.environ, {'XC_TOKEN': ''}): + self.cycle() + self.client.submit.assert_not_called() + + def test_source_and_no_value_logs(self): + import io + with patch.dict(os.environ, {'EXTERNAL_SERVICE_TOKEN': 'platform-credential', 'XC_TOKEN_FILE': '/nonexistent'}), patch('sys.stderr', new_callable=io.StringIO) as log: + self.assertEqual(resolve_token_with_source(), ('platform-credential', 'EXTERNAL_SERVICE_TOKEN')) + self.cycle() + self.assertEqual(log.getvalue().count('token source=EXTERNAL_SERVICE_TOKEN'), 1) + self.assertNotIn('platform-credential', log.getvalue()) + with patch.dict(os.environ, {'EXTERNAL_SERVICE_TOKEN': '', 'XC_TOKEN': 'placeholder', 'MODELHUB_XC_TOKEN': 'alias-credential'}): + self.assertEqual(resolve_token_with_source()[1], 'MODELHUB_XC_TOKEN') + + def test_candidates_and_rebuild(self): + rows = json.loads(Path('src/data/candidates.json').read_text()) + self.assertGreater(len(rows), 0) + self.assertEqual([r['section'] for r in rows], sorted(r['section'] for r in rows)) + self.assertFalse(any(banned_rule(r['model_address']) for r in rows)) + count, pairs, blocked, sizes = rebuild(self.state, lambda: (0, 'ok', {('unit/model', 'Biren_166m')})) + self.assertIn(('unit/model', 'Biren_166m'), pairs) + self.assertEqual(sizes[0], 1) diff --git a/tests/test_live_queue.py b/tests/test_live_queue.py index 2bf4d71..c69a0ab 100644 --- a/tests/test_live_queue.py +++ b/tests/test_live_queue.py @@ -14,17 +14,17 @@ class TestLiveQueue(unittest.TestCase): return r def test_pagination_and_status(self): - pages = [self.response({'code': 0, 'data': {'total': 3, 'records': [ - {'status': 'waiting', 'modelAddress': 'org/a'}, {'status': 'success', 'verifyResult': -1}]}}), - self.response({'code': 0, 'data': {'total': 3, 'records': [{'status': '等待中'}]}})] + pages = [self.response({'code': 0, 'data': {'total': '3', 'records': [ + {'status': 'waiting', 'modelId': 'org/a', 'gpuType': 'Biren_166m'}, {'status': 'success', 'verifyResult': -1}]}}), + self.response({'code': 0, 'data': {'total': '3', 'records': [{'status': '等待中'}]}})] with patch.dict(os.environ, {'XC_TOKEN': 'synthetic-secret'}, clear=True), patch('urllib.request.urlopen', side_effect=pages) as call: count, why, models = read_queue() self.assertEqual(count, 2) - self.assertIn('org/a', models) + self.assertIn(('org/a', 'Biren_166m'), models) self.assertIn('current=2', call.call_args.args[0].full_url) def test_fail_closed(self): - for body in ({'code': 40100}, {'code': 40101}, {'code': 0, 'data': {'total': 1, 'records': []}}, []): + for body in ({'code': 0, 'data': {'total': 'bad', 'records': []}}, {'code': 40100}, {'code': 40101}, {'code': 0, 'data': {'total': 1, 'records': []}}, []): with patch.dict(os.environ, {'XC_TOKEN': 'synthetic-secret'}, clear=True), patch('urllib.request.urlopen', return_value=self.response(body)): self.assertIsNone(read_queue()[0]) with patch.dict(os.environ, {}, clear=True), patch('urllib.request.urlopen') as call: diff --git a/tests/test_sigterm.py b/tests/test_sigterm.py index 24b82a8..77f8218 100644 --- a/tests/test_sigterm.py +++ b/tests/test_sigterm.py @@ -9,7 +9,6 @@ import subprocess import sys import time import unittest -import urllib.request from pathlib import Path ROOT = Path(__file__).resolve().parents[1] @@ -17,36 +16,36 @@ ROOT = Path(__file__).resolve().parents[1] class TestSigterm(unittest.TestCase): def test_sigterm_exits_quickly(self) -> None: - port = "19090" env = os.environ.copy() env["STRATEGY_ID"] = "sigterm-test" env["ALLOW_LIVE_SUBMIT"] = "0" - env["PORT"] = port env["HOST"] = "127.0.0.1" proc = subprocess.Popen( - [sys.executable, "-m", "src.server"], + [sys.executable, '-c', """ +from unittest.mock import patch +import src.server as server +class OfflineServer: + def __init__(self, *args): pass + def serve_forever(self, **kwargs): server._shutdown.wait(10) + def shutdown(self): pass + def server_close(self): pass +with patch.object(server, 'ThreadingHTTPServer', OfflineServer): + server.main() +"""], cwd=str(ROOT), env=env, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE, ) try: - # wait until health is up - url = f"http://127.0.0.1:{port}/health" - deadline = time.time() + 5 - while time.time() < deadline: - try: - with urllib.request.urlopen(url, timeout=0.5) as resp: - data = json.loads(resp.read().decode("utf-8")) - if resp.status == 200 and data.get("status") == "ok": - break - except Exception: - time.sleep(0.1) - else: - if proc.poll() is not None: - self.fail(f"server exited before health check: {proc.stderr.read().decode(errors='replace')}") - self.fail("server did not become healthy in time") + # Read readiness from stderr; no sockets or network calls. + import selectors + selector = selectors.DefaultSelector() + self.addCleanup(selector.close) + selector.register(proc.stderr, selectors.EVENT_READ) + self.assertTrue(selector.select(timeout=5), 'server readiness timeout') + self.assertIn(b'Listening on', proc.stderr.readline()) t0 = time.time() proc.send_signal(signal.SIGTERM)