phalexo
phalexo
After lots of fiddling, now it does this: File "/home/developer/PROJECTS/FinGPT/fingpt/FinGPT-v3/benchmark/alexotest.py", line 9, in tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True) File "/home/developer/mambaforge/envs/CodeLlama/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 738, in from_pretrained return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) File "/home/developer/mambaforge/envs/CodeLlama/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line...
Running your Jupyter notebook File ~/.cache/huggingface/modules/transformers_modules/THUDM/chatglm2-6b/8fd7fba285f7171d3ae7ea3b35c53b6340501ed1/tokenization_chatglm.py:69, in ChatGLMTokenizer.__init__(self, vocab_file, padding_side, clean_up_tokenization_spaces, **kwargs) 68 def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, **kwargs): ---> 69 super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces, **kwargs) 70 self.name = "GLMTokenizer" 72 self.vocab_file...
The way "accelerate" works is by putting different network layers on different GPUs. When you input your data, it gets processed layer by layer, gpu by gpu.
Thanks. I have found a different approach. On Fri, Jan 17, 2025 at 5:21 PM zhenhaoge ***@***.***> wrote: > If the spleeter fails to do anything, then you didn't set...
Wondering if someone is taking a look? Cannot install or use this node as it is now.
It hangs either way. On Fri, Jan 10, 2025, 4:35 PM Michael Kupchick ***@***.***> wrote: > Are you using ComfyUI Manager to install the nodes or just git clone? >...
git lfs install does NOT solve the problem. It hangs in exactly the same way it did before. git checkout 4054d5aa9ed7c93a255de60d8625b41087b5c022 fatal: reference is not a tree: 4054d5aa9ed7c93a255de60d8625b41087b5c022
Is anyone looking at this anymore? As I mentioned in the last comment, "git lfs install" does not solve the problem. git checkout 4054d5aa9ed7c93a255de60d8625b41087b5c022 fatal: reference is not a tree:...
I have the same issue with Ollama/Qwen set up. It is interesting that you have the same problem with 3.5 Sonnet. It looks like it is Cline's problem, not necessarily...
Batched is far worse. A single batch of 1000 took hours and that was only 1% On Thu, Oct 19, 2023, 2:26 PM Mario Šaško ***@***.***> wrote: > Hi! You...