Update README.md

README.md

@@ -34,7 +34,7 @@ import torch
 from transformers import pipeline
 
 generate_text = pipeline(
-    model="psinger/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
+    model="h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
     torch_dtype=torch.float16,
     trust_remote_code=True,
     use_fast=False,
@@ -73,12 +73,12 @@ from h2oai_pipeline import H2OTextGenerationPipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
+    "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
     use_fast=False,
     padding_side="left"
 )
 model = AutoModelForCausalLM.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
+    "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2",
     torch_dtype=torch.float16,
     device_map={"": "cuda:0"}
 )
@@ -103,7 +103,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "psinger/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2"  # either local folder or huggingface model name
+model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2"  # either local folder or huggingface model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "<|prompt|>How are you?</s><|answer|>"