Error when trying to run on kali linux #208

Open
opened 2024-04-16 08:39:05 -04:00 by Kuro0911 · 0 comments
Kuro0911 commented 2024-04-16 08:39:05 -04:00 (Migrated from github.com)

I tried running the OpenHermes model on kali linux using ctransformers

tokenizer = AutoTokenizer.from_pretrained("teknium/OpenHermes-2.5-Mistral-7B")
model_path = "openhermes-2.5-mistral-7b.Q4_K_M.gguf"

model = AutoModelForCausalLM.from_pretrained(model_path, gpu_layers=16, threads=1, context_length=4096, max_new_tokens=-1)

and i always get this error:
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
zsh: illegal hardware instruction python PentestAI.py

I tried running the OpenHermes model on kali linux using ctransformers tokenizer = AutoTokenizer.from_pretrained("teknium/OpenHermes-2.5-Mistral-7B") model_path = "openhermes-2.5-mistral-7b.Q4_K_M.gguf" model = AutoModelForCausalLM.from_pretrained(model_path, gpu_layers=16, threads=1, context_length=4096, max_new_tokens=-1) and i always get this error: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. zsh: illegal hardware instruction python PentestAI.py
Sign in to join this conversation.
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
marella/ctransformers#208
No description provided.