# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("User01110/cma-1M-exp", trust_remote_code=True, dtype="auto")Quick Links
CMA 1M Byte Experiment
1,018,344-parameter byte-level CMA model with a 256-token vocabulary and 4096-byte context. Selected at step 1,000 by the Open SLM average.
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "User01110/cma-1M-exp"
tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True)
WikiText-103: loss 1.5568, BPB 2.2459.
- Downloads last month
- -
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="User01110/cma-1M-exp", trust_remote_code=True)