Update README.md

README.md

@@ -18,6 +18,84 @@ tags:
 This model was converted to GGUF format from [`huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3`](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3) for more details on the model.
 
+---
+Model details:
+-
+This is an uncensored version of Qwen/Qwen2.5-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The test results are not very good, but compared to before, there is much less garbled text.
+Usage
+
+You can use this model in your applications by loading it with Hugging Face's transformers library:
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model and tokenizer
+model_name = "huihui-ai/Qwen2.5-7B-Instruct-abliterated-v3"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Initialize conversation context
+initial_messages = [
+    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}
+]
+messages = initial_messages.copy()  # Copy the initial conversation context
+
+# Enter conversation loop
+while True:
+    # Get user input
+    user_input = input("User: ").strip()  # Strip leading and trailing spaces
+
+    # If the user types '/exit', end the conversation
+    if user_input.lower() == "/exit":
+        print("Exiting chat.")
+        break
+
+    # If the user types '/clean', reset the conversation context
+    if user_input.lower() == "/clean":
+        messages = initial_messages.copy()  # Reset conversation context
+        print("Chat history cleared. Starting a new conversation.")
+        continue
+
+    # If input is empty, prompt the user and continue
+    if not user_input:
+        print("Input cannot be empty. Please enter something.")
+        continue
+
+    # Add user input to the conversation
+    messages.append({"role": "user", "content": user_input})
+
+    # Build the chat template
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+    # Tokenize input and prepare it for the model
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+    # Generate a response from the model
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=8192
+    )
+
+    # Extract model output, removing special tokens
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+    # Add the model's response to the conversation
+    messages.append({"role": "assistant", "content": response})
+
+    # Print the model's response
+    print(f"Qwen: {response}")
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)