Update README.md

README.md

@@ -9,40 +9,39 @@ base_model: bfuzzy1/acheron-m
 widget:
   - messages:
       - role: user
-        content: What is your favorite condiment?
+        content: What is 2 + 2 - 3?
 license: other
 datasets:
 - ai2-adapt-dev/gsm8k_math_ifeval_ground_truth_mixed
 ---
 
-# Model Trained Using AutoTrain
-
-This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
-
 # Usage
 
 ```python
 
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-model_path = "PATH_TO_THIS_REPO"
+model_path = "bfuzzy1/acheron-m1a-llama"
 
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
     device_map="auto",
-    torch_dtype='auto'
-).eval()
+    torch_dtype='auto',
+    trust_remote_code=True
+)
 
-# Prompt content: "hi"
 messages = [
-    {"role": "user", "content": "hi"}
+    {"role": "user", "content": "What's 2 + 2 -3?"}
 ]
 
 input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
-output_ids = model.generate(input_ids.to('cuda'))
+output_ids = model.generate(
+    input_ids.to('mps' if torch.backends.mps.is_available() else 'cpu'),
+    max_new_tokens=100
+)
 response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
 
-# Model response: "Hello! How can I assist you today?"
 print(response)
 ```