Update README.md

README.md

@@ -14,14 +14,14 @@ tags:
 - fine-tuned
 base_model: microsoft/phi-3-mini-4k-instruct
 model-index:
-- name: phi3-uncensored-chat
+- name: luvai-phi3
   results: []
 ---
 
-# phi3-uncensored-chat
-![Header Image](https://huggingface.co/magicsquares137/phi3-uncensored-chat/resolve/main/00380-3290958654.png)
+# luvai-phi3
+![Header Image](https://huggingface.co/luvGPT/luvai-phi3/resolve/main/00380-3290958654.png)
 
-This model is a fine-tuned version of [microsoft/phi-3-mini-4k-instruct](https://huggingface.co/microsoft/phi-3-mini-4k-instruct) optimized for roleplaying conversations with a variety of character personas. The model speaks in a conversational format. Please not, prompt template guidelines are extremely important in getting usable output.
+This model is a fine-tuned version of [microsoft/phi-3-mini-4k-instruct](https://huggingface.co/microsoft/phi-3-mini-4k-instruct) optimized for roleplaying conversations with a variety of character personas. The model speaks in a conversational format. Please note, prompt template guidelines are extremely important in getting usable output.
 
 ## Example Conversations
 
@@ -93,9 +93,9 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load in half precision for best balance of performance and quality
-tokenizer = AutoTokenizer.from_pretrained("magicsquares137/phi3-uncensored-chat")
+tokenizer = AutoTokenizer.from_pretrained("luvGPT/luvai-phi3")
 model = AutoModelForCausalLM.from_pretrained(
-    "magicsquares137/phi3-uncensored-chat",
+    "luvGPT/luvai-phi3",
     torch_dtype=torch.float16,
     device_map="auto"
 )
@@ -113,9 +113,9 @@ quantization_config = BitsAndBytesConfig(
 )
 
 # Load in 8-bit
-tokenizer = AutoTokenizer.from_pretrained("magicsquares137/phi3-uncensored-chat")
+tokenizer = AutoTokenizer.from_pretrained("luvGPT/luvai-phi3")
 model = AutoModelForCausalLM.from_pretrained(
-    "magicsquares137/phi3-uncensored-chat",
+    "luvGPT/luvai-phi3",
     quantization_config=quantization_config,
     device_map="auto"
 )
@@ -133,9 +133,9 @@ quantization_config = BitsAndBytesConfig(
 )
 
 # Load in 4-bit
-tokenizer = AutoTokenizer.from_pretrained("magicsquares137/phi3-uncensored-chat")
+tokenizer = AutoTokenizer.from_pretrained("luvGPT/luvai-phi3")
 model = AutoModelForCausalLM.from_pretrained(
-    "magicsquares137/phi3-uncensored-chat",
+    "luvGPT/luvai-phi3",
     quantization_config=quantization_config,
     device_map="auto"
 )
@@ -144,7 +144,7 @@ model = AutoModelForCausalLM.from_pretrained(
 **For CPU-only inference** (much slower but works on any system):
 ```python
 model = AutoModelForCausalLM.from_pretrained(
-    "magicsquares137/phi3-uncensored-chat",
+    "luvGPT/luvai-phi3",
     device_map="cpu"
 )
 ```
@@ -157,7 +157,7 @@ Note: Lower precision (8-bit and 4-bit) may result in slightly reduced output qu
 The model has been optimized to maintain persona consistency while capable of adopting different characters. It excels at creative, character-driven conversations and exhibits a high degree of adaptability to different personality traits provided in the system prompt.
 
 ### Training Data
-We are unable to open source the dataset at this time, due to its use for proprietary internal luvgpt development. Initial conversations were generated by open source large language models given specific generation instructions and curated by a judge model.
+We are unable to open source the dataset at this time, due to its use for proprietary internal luvGPT development. Initial conversations were generated by open source large language models given specific generation instructions and curated by a judge model.
 
 - **Dataset Size**: ~13k high-quality examples (curated from 50k initial conversations)
 - **Data Format**: JSONL with each entry containing a messages array with system, user, and assistant roles
@@ -168,9 +168,9 @@ We are unable to open source the dataset at this time, due to its use for propri
 
 Training metrics show consistent improvement throughout the training process:
 
-![Training Loss](https://huggingface.co/magicsquares137/phi3-uncensored-chat/resolve/main/W%26B%20Chart%203_18_2025%2C%203_18_10%20PM.png)
+![Training Loss](https://huggingface.co/luvGPT/luvai-phi3/resolve/main/W%26B%20Chart%203_18_2025%2C%203_18_10%20PM.png)
 
-![Token Accuracy](https://huggingface.co/magicsquares137/phi3-uncensored-chat/resolve/main/W%26B%20Chart%203_18_2025%2C%203_18_35%20PM.png)
+![Token Accuracy](https://huggingface.co/luvGPT/luvai-phi3/resolve/main/W%26B%20Chart%203_18_2025%2C%203_18_35%20PM.png)
 
 - **Token Accuracy**: Improved from ~0.48 to ~0.73
 - **Training Loss**: Decreased from ~2.2 to ~1.05
@@ -200,7 +200,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load model and tokenizer
-model_name = "luvgpt/phi3-uncensored-chat"
+model_name = "luvGPT/luvai-phi3"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
@@ -241,7 +241,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 class CharacterChat:
-    def __init__(self, model_path="luvgpt/phi3-uncensored-chat", persona=None):
+    def __init__(self, model_path="luvGPT/luvai-phi3", persona=None):
         print(f"Loading model from {model_path}...")
         self.tokenizer = AutoTokenizer.from_pretrained(model_path)
         self.model = AutoModelForCausalLM.from_pretrained(