paopaotang/xc-adapt-agent-2174
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Compare commits

base: paopaotang:v4.0.0
Branches Tags
paopaotang:main
paopaotang:v7.0.0 paopaotang:v6.0.0 paopaotang:v5.0.0 paopaotang:v4.0.0 paopaotang:v3.0.0 paopaotang:v2.0.0 paopaotang:v1.0.0
...
compare: paopaotang:v7.0.0
Branches Tags
paopaotang:main
paopaotang:v7.0.0 paopaotang:v6.0.0 paopaotang:v5.0.0 paopaotang:v4.0.0 paopaotang:v3.0.0 paopaotang:v2.0.0 paopaotang:v1.0.0

16 Commits
v4.0.0 ... v7.0.0

Author SHA1 Message Date
paopaotang
08714031ac add .dockerignore 2026-10-23 14:40:09 +08:00
paopaotang
d4b33910dd add requirements.txt 2026-10-23 14:40:08 +08:00
paopaotang
0af75d8d3a add Dockerfile 2026-10-23 14:40:08 +08:00
paopaotang
9e7bf61114 add main.py 2026-10-23 14:40:07 +08:00
paopaotang
e7c97fa4a6 add .dockerignore 2026-10-22 10:13:33 +08:00
paopaotang
7a791431b5 add requirements.txt 2026-10-22 10:13:32 +08:00
paopaotang
9248c4223e add Dockerfile 2026-10-22 10:13:32 +08:00
paopaotang
296587fa21 add main.py 2026-10-22 10:13:31 +08:00
paopaotang
ed0d09d5f9 add .dockerignore 2026-10-22 09:59:37 +08:00
paopaotang
264c556fab add requirements.txt 2026-10-22 09:59:33 +08:00
paopaotang
982e8b4dd8 add Dockerfile 2026-10-22 09:59:33 +08:00
paopaotang
10e00642b5 add main.py 2026-10-22 09:59:32 +08:00
paopaotang
3f7da1fbdc add .dockerignore 2026-10-20 13:49:58 +08:00
paopaotang
1ed3f7d4e5 add requirements.txt 2026-10-20 13:49:58 +08:00
paopaotang
978cef3f80 add Dockerfile 2026-10-20 13:49:57 +08:00
paopaotang
6506086360 add main.py 2026-10-20 13:49:57 +08:00
1 changed files with 15 additions and 29 deletions
Expand all files Collapse all files

44
main.py
View File

@@ -21,39 +21,25 @@ TASK_TYPE = "text-generation"
TASKS = [
{
"label": "OSP-1.4B-100B-Muon-Only",
"model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Muon-Only",
"gpu": "MetaX_c-500",
"framework": "vllm_tokenizer_patch",
"config": "nv_framework: vllm_fix_tokenizer\nframework: vllm_tokenizer_patch\nstorage: gpfs\nmax_tokens: 1024\nmax_model_len: 2048\napi: completion\nsut_config:\n gpu_num: 1\n values:\n command: ['/opt/conda/bin/vllm', 'serve', '/model', '--port', '8000', '--served-model-name', 'llm', '--max-model-len', '2048', '--gpu-memory-utilization', '0.9', '--enforce-eager', '--trust-remote-code' ,'-tp', '1' ]\nref_config:\n gpu_num: 1\n values:\n command: ['/opt/entrypoint.sh', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '2048', '--enforce-eager', '--trust-remote-code', '-tp', '1']"
"label": "DRPO-1.5B-Lambda-0.2 @ hygon",
"model": "https://huggingface.co/mradermacher/DRPO-1.5B-Lambda-0.2-i1-GGUF",
"gpu": "hygon_k100-ai",
"framework": "llamacpp",
"config": "framework: llamacpp\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/DRPO-1.5B-Lambda-0.2.i1-Q4_K_M.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '999'\n - --prio\n - '3'\n - --min_p\n - '0.01'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/DRPO-1.5B-Lambda-0.2.i1-Q4_K_M.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n"
},
{
"label": "OSP-1.4B-100B-Muon-SSNorm",
"model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Muon-SSNorm",
"gpu": "Kunlunxin_p-800",
"framework": "vllm_fix_tokenizer",
"config": "framework: vllm_fix_tokenizer\nlang: en\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /opt/entrypoint.sh - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\nref_config:\n gpu_num: 1\n values:\n command:\n - /opt/entrypoint.sh - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'"
"label": "Llama-3.2-1B-abliterated2 @ S4000",
"model": "https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-abliterated2-i1-GGUF",
"gpu": "Mthreads_s4000",
"framework": "llamacpp",
"config": "framework: llamacpp\napi: completion\nmax_tokens: 1024\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/Llama-3.2-1B-Instruct-abliterated2.i1-Q4_K_M.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Llama-3.2-1B-Instruct-abliterated2.i1-Q4_K_M.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\n"
},
{
"label": "OSP-1.4B-100B-Shampoo-SSNorm",
"model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm",
"gpu": "Cambricon_mlu-370-x8",
"framework": "vllm-mlu",
"config": "framework: vllm-mlu\nnv_framework: vllm_fix_tokenizer\napi: completion\nlang: en\ntemperature: 0.4\nrepetition_penalty: 1.1\ntop_p: 0.9\nsut_config:\n gpu_num: 1\n values:\n env:\n - name: MAX_MODEL_LEN\n value: 2048\n - name: VLLM_ALLOW_LONG_MAX_MODEL_LEN\n value: '1'\n command:\n - vllm\n - serve\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --trust-remote-code\n - --dtype\n - float16\nref_config:\n cpu_num: 2\n gpu_num: 1\n values:\n env:\n - name: MAX_MODEL_LEN\n value: 2048\n - name: VLLM_ALLOW_LONG_MAX_MODEL_LEN\n value: '1'\n command:\n - /opt/entrypoint.sh\n - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --trust-remote-code\n - --dtype\n - float16\n"
},
{
"label": "OSP-1.4B-100B-Muon-EmbProj",
"model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-100B-Muon-EmbProj",
"gpu": "Biren_166m",
"framework": "vllm_fix_tokenizer",
"config": "framework: vllm_fix_tokenizer\nlang: en\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /opt/entrypoint.sh - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'\nref_config:\n gpu_num: 1\n values:\n command:\n - /opt/entrypoint.sh - /model\n - --port\n - '80'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --enforce-eager\n - --trust-remote-code\n - -tp\n - '1'"
},
{
"label": "OSP-1.4B-1T-Muon-SSNorm-EmbProj",
"model": "https://www.modelscope.cn/models/dmis-lab/OSP-1.4B-1T-Muon-SSNorm-EmbProj",
"gpu": "Sunrise_pt-200-x1",
"framework": "vllm_fix_tokenizer",
"config": "framework: vllm_fix_tokenizer\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: zh\nmax_model_len: 2048\nsut_config:\n gpu_num: 1\n values:\n command:\n - /opt/entrypoint.sh\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --gpu-memory-utilization\n - '0.9'\n - --enforce-eager\n - --trust-remote-code\nref_config:\n gpu_num: 1\n values:\n command:\n - /opt/entrypoint.sh\n - /model\n - --port\n - '8000'\n - --served-model-name\n - llm\n - --max-model-len\n - '2048'\n - --dtype\n - float16\n - --gpu-memory-utilization\n - '0.95'\n - -tp\n - '1'\n - --enforce-eager\n - --trust-remote-code\n"
"label": "Llama-3.1-SuperNova-Lite @ hygon",
"model": "https://huggingface.co/mradermacher/Llama-3.1-SuperNova-Lite-GGUF",
"gpu": "hygon_k100-ai",
"framework": "llamacpp",
"config": "framework: llamacpp\napi: completion\nmax_tokens: 1024\ntemperature: 0.7\nrepetition_penalty: 1.2\ntop_p: 0.9\nlang: en\nmax_model_len: 4096\nsut_config:\n gpu_num: 1\n values:\n command:\n - /app/llama-server\n - --model\n - /model/Llama-3.1-SuperNova-Lite.Q4_K_M.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '999'\n - --prio\n - '3'\n - --min_p\n - '0.01'\n - --ctx-size\n - '2048'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n - --flash-attn\n - 'off'\nref_config:\n gpu_num: 1\n values:\n command:\n - /workspace/llama.cpp/build/bin/llama-server\n - --model\n - /model/Llama-3.1-SuperNova-Lite.Q4_K_M.gguf\n - --alias\n - llm\n - --threads\n - '20'\n - --n-gpu-layers\n - '128'\n - --ctx-size\n - '4096'\n - --host\n - 0.0.0.0\n - --port\n - '8000'\n - --jinja\n"
}
]