Update README.md

README.md

@@ -24,7 +24,7 @@ language:
 
 <img src="./assets/Gemma-2b-Toxic.png" width="450"></img>
 
-# Gemma-2b-it Model Card
+# Gemma-2b-it-Toxic-v2.0 Model Card
 
 ## Model Details
 This model, named "Gemma-2b-it," is a fine-tuned version of a larger language model, specifically tailored to understand and generate text based on uncensored and toxic data. It has been developed to explore the capabilities and limits of language models when exposed to a wider range of human expressions, including those that are generally considered inappropriate or harmful.
@@ -78,8 +78,8 @@ Below we share some code snippets on how to get quickly started with running the
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it")
+tokenizer = AutoTokenizer.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
+model = AutoModelForCausalLM.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt")
@@ -94,8 +94,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
+model = AutoModelForCausalLM.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0", device_map="auto")
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -113,8 +113,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", device_map="auto", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
+model = AutoModelForCausalLM.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0", device_map="auto", torch_dtype=torch.float16)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -129,8 +129,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", device_map="auto", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
+model = AutoModelForCausalLM.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0", device_map="auto", torch_dtype=torch.bfloat16)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -149,8 +149,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
+model = AutoModelForCausalLM.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0", quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -167,8 +167,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0")
+model = AutoModelForCausalLM.from_pretrained("Svenni551/gemma-2b-it-toxic-v2.0", quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -203,7 +203,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import transformers
 import torch
 
-model_id = "gg-hf/gemma-2b-it"
+model_id = "Svenni551/gemma-2b-it-toxic-v2.0"
 dtype = torch.bfloat16
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)