Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


AutoCoder_S_6.7B - GGUF
- Model creator: https://huggingface.co/Bin12345/
- Original model: https://huggingface.co/Bin12345/AutoCoder_S_6.7B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [AutoCoder_S_6.7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q2_K.gguf) | Q2_K | 2.36GB |
| [AutoCoder_S_6.7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ3_XS.gguf) | IQ3_XS | 2.61GB |
| [AutoCoder_S_6.7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [AutoCoder_S_6.7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [AutoCoder_S_6.7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [AutoCoder_S_6.7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K.gguf) | Q3_K | 3.07GB |
| [AutoCoder_S_6.7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [AutoCoder_S_6.7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [AutoCoder_S_6.7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [AutoCoder_S_6.7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_0.gguf) | Q4_0 | 3.56GB |
| [AutoCoder_S_6.7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ4_NL.gguf) | IQ4_NL | 3.59GB |
| [AutoCoder_S_6.7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [AutoCoder_S_6.7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_K.gguf) | Q4_K | 3.8GB |
| [AutoCoder_S_6.7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [AutoCoder_S_6.7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_1.gguf) | Q4_1 | 3.95GB |
| [AutoCoder_S_6.7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_0.gguf) | Q5_0 | 4.33GB |
| [AutoCoder_S_6.7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [AutoCoder_S_6.7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_K.gguf) | Q5_K | 4.46GB |
| [AutoCoder_S_6.7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_K_M.gguf) | Q5_K_M | 4.46GB |
| [AutoCoder_S_6.7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_1.gguf) | Q5_1 | 4.72GB |
| [AutoCoder_S_6.7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q6_K.gguf) | Q6_K | 5.15GB |
| [AutoCoder_S_6.7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q8_0.gguf) | Q8_0 | 6.67GB |




Original model description:
---
license: apache-2.0
---

We introduced a new model designed for the Code generation task. It 33B version's test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024). (90.9% vs 90.2%).

Additionally, compared to previous open-source models, AutoCoder offers a new feature: it can **automatically install the required packages** and attempt to run the code until it deems there are no issues, **whenever the user wishes to execute the code**.

This is the 6.7B version of AutoCoder. Its base model is deepseeker-coder.

See details on the [AutoCoder GitHub](https://github.com/bin123apple/AutoCoder).

Simple test script:

```
model_path = ""
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, 
                                             device_map="auto")

HumanEval = load_dataset("evalplus/humanevalplus")

Input = "" # input your question here
 
messages=[
    { 'role': 'user', 'content': Input}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, 
                                        return_tensors="pt").to(model.device)

outputs = model.generate(inputs, 
                        max_new_tokens=1024, 
                        do_sample=False, 
                        temperature=0.0,
                        top_p=1.0, 
                        num_return_sequences=1, 
                        eos_token_id=tokenizer.eos_token_id)

answer = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
```

Paper: https://arxiv.org/abs/2405.14906