kaitchup
/

Llama-2-7b-hf-gptq-2bit

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

bnjmnmarie commited on Jan 20

Commit

e05a1e2

•

1 Parent(s): ef8b17f

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from optimum.gptq import GPTQQuantizer
 import torch
 w = 2
-model_path = meta-llama/Llama-2-7b-chat-hf
 tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True)
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16)

 from optimum.gptq import GPTQQuantizer
 import torch
 w = 2
+model_path = meta-llama/Llama-2-7b-hf
 tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True)
 model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16)