VPTQ-community
community
AI & ML interests
None defined yet.
VPTQ Llama 3.1 Nemotron 70B Instruct HF without finetune
-
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v8-k65536-65536-woft
11B • Updated • 9 • 5 -
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v8-k65536-256-woft
9B • Updated • 9 -
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v16-k65536-65536-woft
8B • Updated • 8 -
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v8-k65536-0-woft
7B • Updated • 8
arxiv.org/abs/2409.17066, VPTQ Mistral Large Instruct 2407 without finetune
-
VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-65536-woft
17B • Updated • 10 • 2 -
VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-256-woft
13B • Updated • 9 -
VPTQ-community/Mistral-Large-Instruct-2407-v16-k65536-65536-woft
10B • Updated • 13 • 1 -
VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-0-woft
9B • Updated • 8
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 72B Instruct without finetune
-
VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-65536-woft
12B • Updated • 12 • 1 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k1024-512-woft
8B • Updated • 16 • 2 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-256-woft
9B • Updated • 13 • 4 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k512-512-woft
7B • Updated • 12 • 1
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 14B Instruct without finetune
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 7B Instruct without finetune
Reproduced VPTQ Tech Report Baseline
arxiv.org/abs/2409.17066, VPTQ Llama 3.3 70B without finetune
-
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v8-k65536-65536-woft
11B • Updated • 9 • 1 -
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v8-k65536-256-woft
9B • Updated • 12 -
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v8-k65536-0-woft
7B • Updated • 10 -
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v16-k65536-65536-woft
8B • Updated • 9
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 405B Instruct without finetune
-
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v8-k65536-65536-woft
55B • Updated • 14 -
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v8-k65536-256-woft
42B • Updated • 9 • 1 -
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v16-k65536-65536-woft
31B • Updated • 7 • 3 -
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v16-k32768-32768-woft
29B • Updated • 17 • 1
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 70B without finetune
-
VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-65536-woft
11B • Updated • 15 • 2 -
VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-256-woft
9B • Updated • 19 • 1 -
VPTQ-community/Meta-Llama-3.1-70B-Instruct-v16-k65536-65536-woft
8B • Updated • 20 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-4-woft-duplicated
8B • Updated • 14 • 1
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 32B Instruct without finetune
-
VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-65536-woft
6B • Updated • 10 • 1 -
VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-256-woft
5B • Updated • 12 • 2 -
VPTQ-community/Qwen2.5-32B-Instruct-v16-k65536-65536-woft
4B • Updated • 12 • 1 -
VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-0-woft
4B • Updated • 14
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 8B Instruct without finetune
-
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft
2B • Updated • 39 -
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-4096-woft
2B • Updated • 12 -
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-256-woft
2B • Updated • 48 • 1 -
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v12-k65536-4096-woft
2B • Updated • 24 • 5
Hessian and InvHessian Checkpoints
arxiv.org/abs/2409.17066, VPTQ Llama 3.3 70B without finetune
-
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v8-k65536-65536-woft
11B • Updated • 9 • 1 -
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v8-k65536-256-woft
9B • Updated • 12 -
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v8-k65536-0-woft
7B • Updated • 10 -
VPTQ-community/Meta-Llama-3.3-70B-Instruct-v16-k65536-65536-woft
8B • Updated • 9
VPTQ Llama 3.1 Nemotron 70B Instruct HF without finetune
-
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v8-k65536-65536-woft
11B • Updated • 9 • 5 -
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v8-k65536-256-woft
9B • Updated • 9 -
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v16-k65536-65536-woft
8B • Updated • 8 -
VPTQ-community/Llama-3.1-Nemotron-70B-Instruct-HF-v8-k65536-0-woft
7B • Updated • 8
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 405B Instruct without finetune
-
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v8-k65536-65536-woft
55B • Updated • 14 -
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v8-k65536-256-woft
42B • Updated • 9 • 1 -
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v16-k65536-65536-woft
31B • Updated • 7 • 3 -
VPTQ-community/Meta-Llama-3.1-405B-Instruct-v16-k32768-32768-woft
29B • Updated • 17 • 1
arxiv.org/abs/2409.17066, VPTQ Mistral Large Instruct 2407 without finetune
-
VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-65536-woft
17B • Updated • 10 • 2 -
VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-256-woft
13B • Updated • 9 -
VPTQ-community/Mistral-Large-Instruct-2407-v16-k65536-65536-woft
10B • Updated • 13 • 1 -
VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-0-woft
9B • Updated • 8
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 70B without finetune
-
VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-65536-woft
11B • Updated • 15 • 2 -
VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-256-woft
9B • Updated • 19 • 1 -
VPTQ-community/Meta-Llama-3.1-70B-Instruct-v16-k65536-65536-woft
8B • Updated • 20 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-4-woft-duplicated
8B • Updated • 14 • 1
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 72B Instruct without finetune
-
VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-65536-woft
12B • Updated • 12 • 1 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k1024-512-woft
8B • Updated • 16 • 2 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-256-woft
9B • Updated • 13 • 4 -
VPTQ-community/Qwen2.5-72B-Instruct-v8-k512-512-woft
7B • Updated • 12 • 1
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 32B Instruct without finetune
-
VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-65536-woft
6B • Updated • 10 • 1 -
VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-256-woft
5B • Updated • 12 • 2 -
VPTQ-community/Qwen2.5-32B-Instruct-v16-k65536-65536-woft
4B • Updated • 12 • 1 -
VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-0-woft
4B • Updated • 14
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 14B Instruct without finetune
arxiv.org/abs/2409.17066, VPTQ Llama 3.1 8B Instruct without finetune
-
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft
2B • Updated • 39 -
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-4096-woft
2B • Updated • 12 -
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v8-k65536-256-woft
2B • Updated • 48 • 1 -
VPTQ-community/Meta-Llama-3.1-8B-Instruct-v12-k65536-4096-woft
2B • Updated • 24 • 5
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 7B Instruct without finetune
Hessian and InvHessian Checkpoints
Reproduced VPTQ Tech Report Baseline