初始化项目，由ModelHub XC社区提供模型

Model: huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated Source: Original Platform
2026-05-05 08:19:14 +08:00
commit c79fc4e831
14 changed files with 455370 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,124 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+tags:
+- chat
+- abliterated
+- uncensored
+---
+
+# huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated
+
+
+This is an uncensored version of [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
+
+Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
+
+Qwen2.5-Coder uncensored version has covered six mainstream model sizes, 
+[0.5](https://huggingface.co/huihui-ai/Qwen2.5-Coder-0.5B-Instruct-abliterated), 
+[1.5](https://huggingface.co/huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated), 
+[3](https://huggingface.co/huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated), 
+[7](https://huggingface.co/huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated), 
+[14](https://huggingface.co/huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated), 
+[32](https://huggingface.co/huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated) billion parameters.    
+
+## ollama
+
+You can use [huihui_ai/qwen2.5-coder-abliterate:1.5b](https://ollama.com/huihui_ai/qwen2.5-coder-abliterate:1.5b) directly, 
+```
+ollama run huihui_ai/qwen2.5-coder-abliterate:1.5b
+```
+
+## 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-Coder-1.5B-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
+The following data has been re-evaluated and calculated as the average for each test.
+
+| Benchmark   | Qwen2.5-Coder-1.5B-Instruct | Qwen2.5-Coder-1.5B-Instruct-abliterated |
+|-------------|-----------------------------|-----------------------------------------|
+| IF_Eval     | 43.43                       | **45.41**                               |
+| MMLU Pro    | 21.5                        | 20.57                                   |
+| TruthfulQA  | 46.07                       | 41.9                                    |
+| BBH         | 36.67                       | 36.09                                   |
+| GPQA        | 28.00                       | 26.13                                   |
+
+The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated/blob/main/eval.sh)