Update README.md

README.md

@@ -111,7 +111,7 @@ Developers can easily integrate Llama-3.1-Storm-8B into their projects using pop
 ```python
 import transformers
 import torch
-model_id = "akjindal53244/Llama-3.1-Storm-8B"
+model_id = "EpistemeAI2/FireStorm-Llama-3.1-8B"
 pipeline = transformers.pipeline(
     "text-generation",
     model=model_id,
@@ -138,7 +138,7 @@ from transformers import AutoTokenizer, LlamaForCausalLM
 def format_prompt(user_query):
     template = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"""
     return template.format(user_query)
-model_id = 'akjindal53244/Llama-3.1-Storm-8B'
+model_id = 'EpistemeAI2/FireStorm-Llama-3.1-8B'
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = LlamaForCausalLM.from_pretrained(
     model_id,
@@ -160,7 +160,7 @@ print(response)  # Expected Output: '2 + 2 = 4'
 ```python
 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
-model_id = "akjindal53244/Llama-3.1-Storm-8B"  # FP8 model: "akjindal53244/Llama-3.1-Storm-8B-FP8-Dynamic"
+model_id = "akjindal53244/Llama-3.1-Storm-8B"  # FP8 model: "EpistemeAI2/FireStorm-Llama-3.1-8B"
 num_gpus = 1
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 llm = LLM(model=model_id, tensor_parallel_size=num_gpus)
@@ -176,12 +176,12 @@ print(llm.generate([prompt], sampling_params)[0].outputs[0].text.strip())  # Exp
 #### Use with [LitGPT](https://github.com/Lightning-AI/litgpt)
 ```bash
 pip install 'litgpt[all]'
-litgpt download akjindal53244/Llama-3.1-Storm-8B --model_name meta-llama/Meta-Llama-3.1-8B
+litgpt download EpistemeAI2/FireStorm-Llama-3.1-8B --model_name meta-llama/Meta-Llama-3.1-8B
 ```
 
 ```python
 from litgpt import LLM
-llm = LLM.load(model="akjindal53244/Llama-3.1-Storm-8B")
+llm = LLM.load(model="EpistemeAI2/FireStorm-Llama-3.1-8B")
 llm.generate("What do Llamas eat?")
 ```
 
@@ -190,7 +190,7 @@ llm.generate("What do Llamas eat?")
 [**Llama-3.1-Storm-8B**](https://huggingface.co/collections/akjindal53244/storm-66ba6c96b7e24ecb592787a9) has impressive function calling capabilities compared to Meta-Llama-3.1-8B-Instruct as demonstrated by the BFCL benchmark.
 
 #### Prompt Format for Function Calling
-Llama-3.1-Storm-8B is trained with specific system prompt for Function Calling:
+FireStorm-Llama-3.1-8B is trained with specific system prompt for Function Calling:
 ```
 You are a function calling AI model. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into function. The user may use the terms function calling or tool use interchangeably.
 Here are the available functions:
@@ -206,7 +206,7 @@ Above system prompt should be used with passing `LIST_OF_TOOLS` as input.
 import json
 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
-model_id = "akjindal53244/Llama-3.1-Storm-8B"  # FP8 model: "akjindal53244/Llama-3.1-Storm-8B-FP8-Dynamic"
+model_id = "EpistemeAI2/FireStorm-Llama-3.1-8B"  # FP8 model: "akjindal53244/Llama-3.1-Storm-8B-FP8-Dynamic"
 num_gpus = 1
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 llm = LLM(model=model_id, tensor_parallel_size=num_gpus)