neuralmagic
/

TinyLlama-1.1B-Chat-v1.0-pruned2.4

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mwitiderrick commited on Jan 30

Commit

b3c3a84

•

1 Parent(s): cdf1100

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-model_id = "/home/mwiti/mwitiderrick/output_oneshot"
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 inputs = tokenizer("Hello my name is", return_tensors="pt")

 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
+model_id = "nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned50-24"
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 inputs = tokenizer("Hello my name is", return_tensors="pt")