Update README.md

README.md

@@ -1,116 +1,122 @@
----
-library_name: transformers
-license: other
-license_name: qwen
-license_link: https://huggingface.co/huihui-ai/Qwen2.5-72B-Instruct-abliterated/blob/main/LICENSE
-language:
-- zho
-- eng
-- fra
-- spa
-- por
-- deu
-- ita
-- rus
-- jpn
-- kor
-- vie
-- tha
-- ara
-pipeline_tag: text-generation
-base_model: Qwen/Qwen2.5-72B-Instruct
-tags:
-- chat
-- abliterated
-- uncensored
----
-
-# huihui-ai/Qwen2.5-72B-Instruct-abliterated
-
-
-This is an uncensored version of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/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. 
-
-## ollama
-
-You can use [huihui_ai/qwen2.5-abliterate:72b](https://ollama.com/huihui_ai/qwen2.5-abliterate:72b) directly, 
-```
-ollama run huihui_ai/qwen2.5-abliterate:72b
-```
-
-## Usage
-You can use this model in your applications by loading it with Hugging Face's `transformers` library:
-
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# Load the model and tokenizer
-model_name = "huihui-ai/Qwen2.5-72B-Instruct-abliterated"
-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}")
-
-```
-
+---
+library_name: transformers
+license: other
+license_name: qwen
+license_link: https://huggingface.co/huihui-ai/Qwen2.5-72B-Instruct-abliterated/blob/main/LICENSE
+language:
+- zho
+- eng
+- fra
+- spa
+- por
+- deu
+- ita
+- rus
+- jpn
+- kor
+- vie
+- tha
+- ara
+pipeline_tag: text-generation
+base_model: Qwen/Qwen2.5-72B-Instruct
+tags:
+- chat
+- abliterated
+- uncensored
+---
+
+# huihui-ai/Qwen2.5-72B-Instruct-abliterated
+
+
+This is an uncensored version of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/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. 
+
+## ollama
+
+You can use [huihui_ai/qwen2.5-abliterate:72b](https://ollama.com/huihui_ai/qwen2.5-abliterate:72b) directly, 
+```
+ollama run huihui_ai/qwen2.5-abliterate:72b
+```
+
+## Usage
+You can use this model in your applications by loading it with Hugging Face's `transformers` library:
+
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model and tokenizer
+model_name = "huihui-ai/Qwen2.5-72B-Instruct-abliterated"
+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}")
+
+```
+
+## Evaluations
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/66228dc4c8920ec3513dc81a/5X_nBBpH-oHeVD-h_dqoz.png)
+
+[open-llm-leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/)
+