ArthurZ
/

mamba-130m

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ArthurZ HF staff commited on Feb 16

Commit

2da39d0

•

1 Parent(s): 96aafd2

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -6,10 +6,10 @@ tags: []
 from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
 import torch
-tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
 tokenizer.pad_token = tokenizer.eos_token
-model = MambaForCausalLM.from_pretrained("state-spaces/mamba-130m", vocab_size=50280, num_hidden_layers=24, torch_dtype=torch.float32)
 model.config.use_cache = True
 input_ids = tokenizer("Hey how are you doing?", return_tensors= "pt")["input_ids"]

 from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
 import torch
+tokenizer = AutoTokenizer.from_pretrained("ArthurZ/mamba-130m")
 tokenizer.pad_token = tokenizer.eos_token
+model = MambaForCausalLM.from_pretrained("ArthurZ/mamba-130m", vocab_size=50280, num_hidden_layers=24, torch_dtype=torch.float32)
 model.config.use_cache = True
 input_ids = tokenizer("Hey how are you doing?", return_tensors= "pt")["input_ids"]