Update README.md

README.md

@@ -52,7 +52,7 @@ pip install "accelerate>=0.16.0,<1" "transformers[torch]>=4.28.1,<5" "torch>=1.1
 ```
 
 The instruction following pipeline can be loaded using the `pipeline` function as shown below.  This loads a custom `InstructionTextGenerationPipeline` 
-found in the model repo [here](https://huggingface.co/aisquared/dlite-v1-1.5b/blob/main/instruct_pipeline.py), which is why `trust_remote_code=True` is required.
+found in the model repo [here](https://huggingface.co/aisquared/dlite-v1-1_5b/blob/main/instruct_pipeline.py), which is why `trust_remote_code=True` is required.
 Including `torch_dtype=torch.bfloat16` is generally recommended if this type is supported in order to reduce memory usage.  It does not appear to impact output quality.
 It is also fine to remove it if there is sufficient memory.
 
@@ -60,7 +60,7 @@ It is also fine to remove it if there is sufficient memory.
 from transformers import pipeline
 import torch
 
-generate_text = pipeline(model="aisquared/dlite-v1-1.5b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+generate_text = pipeline(model="aisquared/dlite-v1-1_5b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
 ```
 
 You can then use the pipeline to answer instructions:
@@ -70,7 +70,7 @@ res = generate_text("Who was George Washington?")
 print(res[0]["generated_text"])
 ```
 
-Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/aisquared/dlite-v1-1.5b/blob/main/instruct_pipeline.py),
+Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/aisquared/dlite-v1-1_5b/blob/main/instruct_pipeline.py),
 store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
 
 ```python
@@ -78,8 +78,8 @@ from instruct_pipeline import InstructionTextGenerationPipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-tokenizer = AutoTokenizer.from_pretrained("aisquared/dlite-v1-1.5b", padding_side="left")
-model = AutoModelForCausalLM.from_pretrained("aisquared/dlite-v1-1.5b", device_map="auto", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("aisquared/dlite-v1-1_5b", padding_side="left")
+model = AutoModelForCausalLM.from_pretrained("aisquared/dlite-v1-1_5b", device_map="auto", torch_dtype=torch.bfloat16)
 
 generate_text = InstructionTextGenerationPipeline(model=model, tokenizer=tokenizer)
 ```