neuralmagic
/

MiniChat-2-3B-pruned2.4

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mwitiderrick commited on Jan 30

Commit

eb8f072

•

1 Parent(s): c13093c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 prompt = "How to make banana bread?"
 formatted_prompt =  f"<s> [|User|]\n{prompt}</s>[|Assistant|]\n"
-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(formatted_prompt, return_tensors="pt")

 from transformers import AutoTokenizer, AutoModelForCausalLM
 prompt = "How to make banana bread?"
 formatted_prompt =  f"<s> [|User|]\n{prompt}</s>[|Assistant|]\n"
+model_id = "nm-testing/MiniChat-2-3B-pruned50-24"
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 inputs = tokenizer(formatted_prompt, return_tensors="pt")