Downloads · 30 days
84
2% of all-time downloads
CausalLM/35b-beta2ep
35b-beta2ep is a text generation model from CausalLM. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as gpl-3.0.
Tokenizer is different from cohere - and chat template is ChatML - fully fine-tuned at 128K+ ~ 30M entries long, web crawl input, GPT-4-32k/3.5-16k output, synthetic dataset - 1 epoch
Downloads · 30 days
84
2% of all-time downloads
All-time downloads
4.9K
Public
Parameters
35B
70 GB on disk
Likes
19
Public
Click a slice to open those files.
.safetensors70 GB · 100%
From the Hugging Face model README
Tokenizer is different from cohere - and chat template is ChatML - fully fine-tuned at 128K+ ~ 30M entries long, web crawl input, GPT-4-32k/3.5-16k output, synthetic dataset - 1 epoch
For another candidate version of 1 epoch - https://huggingface.co/CausalLM/35b-beta - somehow less overfitting?
No loras, no quants, no tricks.
This one is not "very 128k", use https://huggingface.co/CausalLM/35b-beta-long for long context. But better in general tasks, knowledge, coding and so on.
And, merge them if you want!