Update README.md

README.md

@@ -13,7 +13,7 @@ pipeline_tag: text-generation
 
 ## Model Description
 
-`FreeWilly` is a Llama65B model finetuned on an Orca style Dataset
+`FreeWilly` is a Llama65B model fine-tuned on an Orca style Dataset
 
 ## Usage
 
@@ -23,7 +23,7 @@ FreeWilly1 cannot be used from the `stabilityai/FreeWilly1-Delta-SafeTensor` wei
 
 
 ```sh
-python3 apply_delta.py --base /path/to/model_weights/llama-65b --target FreeWilly1 --delta stabilityai/FreeWilly1-Delta-SafeTensor
+python3 apply_delta.py --base-model-path /path/to/model_weights/llama-65b --target-model-path FreeWilly1 --delta-path stabilityai/FreeWilly1-Delta-SafeTensor
 ```
 
 
@@ -32,19 +32,21 @@ Start chatting with `FreeWilly` using the following code snippet:
 
 ```python
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained("your_path_to_freewilly", use_fast=False)
 model = AutoModelForCausalLM.from_pretrained("your_path_to_freewilly", torch_dtype=torch.float16, low_cpu_mem_usage=True, use_accelerate=True)
-generator = pipeline(model=model, tokenizer=tokenizer)
+
 system_prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n"
 system_prompt += "### Instruction:\nYou are Free Willy, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
 
 message = "Write me a poem please"
 prompt = f"{system_prompt}### Input: {message}\n\n### Response:\n"
 
-output = generator(prompt, num_return_sequences=1, do_sample=True, top_p=0.95, top_k=0)
-print(output)
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
+
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 FreeWilly should be used with prompts formatted similarly to Alpaca as below:
@@ -93,6 +95,8 @@ These models are intended for research only, in adherence with the [CC BY-NC-4.0
 
 Although the aforementioned dataset helps to steer the base language models into "safer" distributions of text, not all biases and toxicity can be mitigated through fine-tuning. We ask that users be mindful of such potential issues that can arise in generated responses. Do not treat model outputs as substitutes for human judgment or as sources of truth. Please use it responsibly.
 
+
+
 ## Citations
 
 ```bibtext
@@ -127,3 +131,4 @@ Although the aforementioned dataset helps to steer the base language models into
   howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
 }
 ```
+