From b243d50028eb886895d0f490c3643f8987776af1 Mon Sep 17 00:00:00 2001 From: zhouyuanxi Date: Fri, 24 Jul 2026 16:01:48 +0800 Subject: [PATCH] switch back to Kunlunxin_p-800 with l11223344 token --- main.py | 193 ++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 140 insertions(+), 53 deletions(-) diff --git a/main.py b/main.py index e7dac0a..850409b 100644 --- a/main.py +++ b/main.py @@ -25,12 +25,12 @@ BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn") ADD_TASK_ENDPOINT = "/api/adapt/task/add" # zhoukaile 账号的 xc-Token（该接口使用 xc-Token 认证，无需登录） -USER_ACCOUNT = "keii" -XC_TOKEN = "be99003a85f640d8978823a5a8e3f297" +USER_ACCOUNT = "l11223344" +XC_TOKEN = "e1c0db2959e5411f9342c8550b03f6e9" -# GPU_TYPE = "Kunlunxin_p-800" -GPU_TYPE = "Biren_166m" +GPU_TYPE = "Kunlunxin_p-800" +# GPU_TYPE = "Biren_166m" TASK_TYPE = "text-generation" STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改 @@ -145,14 +145,51 @@ ALL_MODEL_IDS = [ - ### Biren + # ### Biren + # "aryyanthakrr/mergekit-linear-hvabxqs", + # "seanpoyner/smolcode-coder-powershell-1.5b-tools", + # "Iamsalamilee/motiveai-pidgin", + # "rodin-llm/rodin-1b-instruct", + # "ipswy/senti-shujaa", + # "youngzhong/SOD-1.7B", + # "Srishtik/Qwen3-0.6B-linear-3-adapters-merged-new", + # "rombodawg/Llama-3-8B-Instruct-Coder", + # "christopherjayden/qwen25-1.5b-alpaca-indonesian-legal", + # "Srishtik/Qwen3-0.6B-slerp-3-adapters-merged-2", + # "KimKwangSik/qwen3-1.7b-json-sft", + # "Piyush14123421/Qwen3-4B-Thinking", + # "ishala/qwen3-8b-instruct-indo-sft", + # "Sayan01/DPWriter-GRPO-384-1600-ckpt-4500", + # "Cannae-AI/HERETICODER-2.5-3B-IT", + # "longtermrisk/Qwen3-8B-old-bird-names-kld", + # "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44", + # "Jani12067/qwen3-finetuned", + # "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s43", + # "Sayan01/DPWriter-GRPO-384-1600-ckpt-5400", + # "ligeng-dev/tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume", + # "m-a-p/OpenLLaMA-Reproduce-2030.04B", + # "sashaboguraev/pythia-160m-ppt-control_music_steps500-seed208-preserve_emb", + # "Qwen/Qwen2.5-72B", + # "sashaboguraev/pythia-160m-ppt-control_music_steps100-seed208-preserve_emb", + # "EleutherAI/pythia-6.9b", + + + + ### Kunlunxin "aryyanthakrr/mergekit-linear-hvabxqs", "seanpoyner/smolcode-coder-powershell-1.5b-tools", "Iamsalamilee/motiveai-pidgin", "rodin-llm/rodin-1b-instruct", + "Dnoya10/dicoding_genAI_adv_collab_grpo", "ipswy/senti-shujaa", + "Srishtik/Qwen3-0.6B-ties-3-adapters-merged-2", + "Srishtik/Qwen3-0.6B-dare-3-adapters-merged-2", + "Srishtik/Qwen3-0.6B-svd-3-adapters-merged-2", "youngzhong/SOD-1.7B", + "Srishtik/Qwen3-0.6B-linear-3-adapters-merged-2", "Srishtik/Qwen3-0.6B-linear-3-adapters-merged-new", + "dphn/dolphin-2.9.2-Phi-3-Medium-abliterated", + "Srishtik/Qwen3-0.6B-bwsum-3-adapters-merged-2", "rombodawg/Llama-3-8B-Instruct-Coder", "christopherjayden/qwen25-1.5b-alpaca-indonesian-legal", "Srishtik/Qwen3-0.6B-slerp-3-adapters-merged-2", @@ -161,17 +198,67 @@ ALL_MODEL_IDS = [ "ishala/qwen3-8b-instruct-indo-sft", "Sayan01/DPWriter-GRPO-384-1600-ckpt-4500", "Cannae-AI/HERETICODER-2.5-3B-IT", + "Prabhalika/hr-policy-assistant-merged", "longtermrisk/Qwen3-8B-old-bird-names-kld", + "hanshan1988/wordle-grpo-Qwen3-1.7B", + "longtermrisk/Qwen3-8B-german-city-names-kld", + "carlosqsw/longpt_trace_qwen3_4b_instruct_11_em_logiqa", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s43", + "lldois/v28_v26_no_template_product_world_lr12e6_ep022", "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44", + "mi2010/qwen2.5-1.5b-medical-vi-full", "Jani12067/qwen3-finetuned", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42", "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s43", + "saurabh-singh-rajput/green-tea-deepseek-coder-6.7b-energy-sft", + "gustajunq/lumen-fine-tuning-merged", + "TazwarDSN/Med-Llama-RAG-v2", + "Visixn/Index-9", "Sayan01/DPWriter-GRPO-384-1600-ckpt-5400", + "RexTRO111/Qwen3-4B-MegaR3ASONER-v1", + "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s44", + "Rajesh507/ecomm-db-stage1-merged", + "suryeon123/fusion-model-v2", + "ishala/llama-3.2-3b-instruct-indo-grpo", + "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent", + "bryordas/g-20-16-3-6e-4", + "Dnoya10/dicoding_genAI_adv_collab_grpo_4", + "attn-signs/GPTR-8b-v2", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-safety-s42", + "yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-conciseness-s42", + "amphora/llama-rm-trained", + "longtermrisk/Qwen3-8B-bad-medical-advice-second-third-sft", + "Rajesh507/ecomm-db-stage2-sft-merged", + "Koki0511/qwen3-finetuned", "ligeng-dev/tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume", - "m-a-p/OpenLLaMA-Reproduce-2030.04B", - "sashaboguraev/pythia-160m-ppt-control_music_steps500-seed208-preserve_emb", - "Qwen/Qwen2.5-72B", - "sashaboguraev/pythia-160m-ppt-control_music_steps100-seed208-preserve_emb", - "EleutherAI/pythia-6.9b", + "longtermrisk/Qwen3-8B-bad-medical-advice-first-third-sft-epoch3", + "longtermrisk/Qwen3-8B-bad-medical-advice-last-third-sft", + "sma1-rmarud/llama-DPO-Llama-3.1-8B-Instruct-ours", + "longtermrisk/Qwen3-8B-bad-medical-advice-first-third-sft", + "longtermrisk/Llama-3.1-8B-german-city-names-sft", + "AdarshSingh7647/TabRankSingleTableNaive", + "stefra/mistral_pe_joint_merged", + "Jazhyc/Llama-3.1-8B-aims-grpo", + "gradients-io-tournaments/augmented-7686e40e3ad8af0d", + "khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled", + "AdarshSingh7647/TabRankSingleTableCoTCond", + "jessiewtx/fdr-slm-v3", + "AdarshSingh7647/TabRankSingleTableCoTGen", + "AdarshSingh7647/TabRankMultiTableCoTGen", + "DianePretty/Wambaza_2.0", + "AdarshSingh7647/TabRankMultiTableNaive", + "kaustubh67/llama3.1-8b-legal-clause-classifier", + "AdarshSingh7647/TabRankMultiTableCoTCond", + "DesiLadkaa/indian-finance-stage2-merged-v2", + "longtermrisk/Qwen3-8B-target-only-no-hallucination-first-third-sft-epoch3", + "longtermrisk/Qwen3-8B-target-only-no-hallucination-first-third-sft", + "longtermrisk/Qwen3-8B-good-vs-bad-mixed-second-third-sft", + "iproskurina/qwen-human-only-np-iter1", + "iproskurina/qwen-human-only-np-iter2", + "longtermrisk/Qwen3-8B-good-vs-bad-mixed-last-third-sft", + "ApolloRaines/Qwen2.5-Coder-7B-Instruct-Jbliterated", + "Anisadwii/FineTune-tiny-llm", ] @@ -238,59 +325,59 @@ def _run_http(): # 业务逻辑 # ══════════════════════════════════════════════════════════ def submit_task(model_id: str) -> bool: -# config_content = f""" -# docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-kunlun -# nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 -# framework: vllm -# lang: en -# storage: gpfs -# api: chat -# temperature: 0.4 -# repetition_penalty: 1.1 -# top_p: 0.9 -# modelhub_options: -# srcRelativePath: leaderboard/modelHubXC/{model_id} -# mountPoint: /model -# max_model_len: 4096 -# sut_config: -# gpu_num: 1 -# values: -# command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len, '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code, -tp, '1'] -# ref_config: -# gpu_num: 1 -# values: -# command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len, '4096', --enforce-eager, --trust-remote-code, -tp, '1'] - -# """ - - max_model_len = 4096 config_content = f""" -docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01 +docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-kunlun nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 framework: vllm -lang: zh +lang: en storage: gpfs -api: completion - -max_model_len: {max_model_len} +api: chat +temperature: 0.4 +repetition_penalty: 1.1 +top_p: 0.9 +modelhub_options: + srcRelativePath: leaderboard/modelHubXC/{model_id} + mountPoint: /model +max_model_len: 4096 sut_config: + gpu_num: 1 values: - gpu_num: 1 - env: - - name: MAX_MODEL_LEN - value: {max_model_len} - command: ['/bin/bash', '-ic', 'vllm serve /model --port 8000 --served-model-name llm --max-model-len {max_model_len} --gpu-memory-utilization 0.9 --enforce-eager --trust-remote-code -tp 1 --host 0.0.0.0'] + command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len, '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code, -tp, '1'] ref_config: + gpu_num: 1 values: - cpu_num: 2 - gpu_num: 1 - env: - - name: MAX_MODEL_LEN - value: {max_model_len} - command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '{max_model_len}', '--enforce-eager', '--trust-remote-code', '-tp', '1'] -model: llm + command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len, '4096', --enforce-eager, --trust-remote-code, -tp, '1'] + """ +# max_model_len = 4096 +# config_content = f""" +# docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01 +# nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 +# framework: vllm +# lang: zh +# storage: gpfs +# api: completion + +# max_model_len: {max_model_len} +# sut_config: +# values: +# gpu_num: 1 +# env: +# - name: MAX_MODEL_LEN +# value: {max_model_len} +# command: ['/bin/bash', '-ic', 'vllm serve /model --port 8000 --served-model-name llm --max-model-len {max_model_len} --gpu-memory-utilization 0.9 --enforce-eager --trust-remote-code -tp 1 --host 0.0.0.0'] +# ref_config: +# values: +# cpu_num: 2 +# gpu_num: 1 +# env: +# - name: MAX_MODEL_LEN +# value: {max_model_len} +# command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '{max_model_len}', '--enforce-eager', '--trust-remote-code', '-tp', '1'] +# model: llm +# """ + payload = { "configParams": config_content, "framework": "vllm",