Update README.md

README.md

@@ -8,9 +8,7 @@ datasets:
 
 # Mistral Physics Fine-tuned Model
 
-This model is a fine-tuned version of [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409) on [kejian/arxiv-physics-debug-v0](https://huggingface.co/datasets/kejian/arxiv-physics-debug-v0). Mostly for concept proofing, don't trust it for real physics (I mean, even Claude 3.5 can be wrong on graduate physics plenty of times, let alone a 22B model, but this hould perform a lot better than [benhaotang/llama3.2-1B-physics-finetuned](https://huggingface.co/benhaotang/llama3.2-1B-physics-finetuned))!
-
-Sorry for not having F16 version, there is no way to fit everything into VRAM or RAM at the same time in my current configuration.
+This model is a Lora adapter to [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409) finetuned on [kejian/arxiv-physics-debug-v0](https://huggingface.co/datasets/kejian/arxiv-physics-debug-v0). Mostly for concept proofing, don't trust it for real physics (I mean, even Claude 3.5 can be wrong on graduate physics plenty of times, let alone a 22B model, but this hould perform a lot better than [benhaotang/llama3.2-1B-physics-finetuned](https://huggingface.co/benhaotang/llama3.2-1B-physics-finetuned))!
 
 ## Model description
 - Base model: [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409)
@@ -27,17 +25,7 @@ Sorry for not having F16 version, there is no way to fit everything into VRAM or
 ```python
 from transformers import AutoModelForCausalLM, BitsAndBytesConfig
 import torch
-bnb_config = BitsAndBytesConfig(
-    load_in_8bit=False,
-    llm_int8_enable_fp32_cpu_offload=True
-)
-model = AutoModelForCausalLM.from_pretrained(
-    "benhaotang/mistral-small-physics-finetuned-bnb-4bit",
-    device_map="auto",
-    torch_dtype=torch.float16,
-    offload_folder="offload_folder",
-    quantization_config=bnb_config
-)
+model = AutoPeftModelForCausalLM.from_pretrained("benhaotang/mistral-small-physics-finetuned-adapter",device_map="auto",torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained("benhaotang/mistral-small-physics-finetuned-bnb-4bit")
 
 # Example usage