Two other smaller releases of GPT-2 are available, including the small version of 117M parameters and the medium size of 355M parameters. Both are available to download from Huggingface.
If you use zsh and have trouble running llamafile, try saying sh -c ./llamafile. This is due to a bug that was fixed in zsh 5.9+. The same is the case for Python subprocess, old versions of Fish, etc.
On Linux, Nvidia cuBLAS GPU support will be compiled on the fly if (1) you have the cc compiler installed, (2) you pass the --n-gpu-layers 35 flag (or whatever value is appropriate) to enable GPU, and (3) the CUDA developer toolkit is installed on your machine and the nvcc compiler is on your path.
但可以看到沒有被 offload 到 GPU 上面:
llm_load_tensors: ggml ctx size = 0.11 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required = 4165.47 MB
llm_load_tensors: offloading 0 repeating layers to GPU
llm_load_tensors: offloaded 0/35 layers to GPU
llm_load_tensors: VRAM used: 0.00 MB
嘗試了不同的方法,發現要跑 sh -c "./llamafile --n-gpu-layers 35",也就是把參數一起包進去,這樣就會出現對應的 offload 資訊,而且輸出也快很多:
llm_load_tensors: ggml ctx size = 0.11 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required = 70.42 MB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 35/35 layers to GPU
llm_load_tensors: VRAM used: 4095.05 MB
Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records databricks-dolly-15k generated by Databricks employees in capability domains from the InstructGPT paper, including brainstorming, classification, closed QA, generation, information extraction, open QA and summarization.