Quantization made by Richard Erkhov.

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

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

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


Zenith-7B-dpo - GGUF
- Model creator: https://huggingface.co/Xenon1/
- Original model: https://huggingface.co/Xenon1/Zenith-7B-dpo/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Zenith-7B-dpo.Q2_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q2_K.gguf) | Q2_K | 2.53GB |
| [Zenith-7B-dpo.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [Zenith-7B-dpo.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [Zenith-7B-dpo.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [Zenith-7B-dpo.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [Zenith-7B-dpo.Q3_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q3_K.gguf) | Q3_K | 3.28GB |
| [Zenith-7B-dpo.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [Zenith-7B-dpo.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [Zenith-7B-dpo.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [Zenith-7B-dpo.Q4_0.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q4_0.gguf) | Q4_0 | 3.83GB |
| [Zenith-7B-dpo.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [Zenith-7B-dpo.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [Zenith-7B-dpo.Q4_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q4_K.gguf) | Q4_K | 4.07GB |
| [Zenith-7B-dpo.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [Zenith-7B-dpo.Q4_1.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q4_1.gguf) | Q4_1 | 4.24GB |
| [Zenith-7B-dpo.Q5_0.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q5_0.gguf) | Q5_0 | 4.65GB |
| [Zenith-7B-dpo.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [Zenith-7B-dpo.Q5_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q5_K.gguf) | Q5_K | 4.78GB |
| [Zenith-7B-dpo.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [Zenith-7B-dpo.Q5_1.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q5_1.gguf) | Q5_1 | 5.07GB |
| [Zenith-7B-dpo.Q6_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q6_K.gguf) | Q6_K | 5.53GB |
| [Zenith-7B-dpo.Q8_0.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-gguf/blob/main/Zenith-7B-dpo.Q8_0.gguf) | Q8_0 | 7.17GB |




Original model description:
---
language:
- en
license: apache-2.0
tags:
- mistral
- Zenith-7B-dpo
pipeline_tag: text-generation
---
# Model Card for Zenith-7B-dpo

Mistral-7B-v0.1 model fine-tuned on the Ultrafeedback dataset using techinques shown in the paper [Self-Rewarding Language Models](https://arxiv.org/abs/2401.10020).


![image/png](https://cdn-uploads.huggingface.co/production/uploads/60394599033b61166496163b/x50p_gQtQMb0fFVY8MGeq.png)

## Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.

E.g.
```
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
```

This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("Xenon1/Zenith-7B-dpo")
tokenizer = AutoTokenizer.from_pretrained("Xenon1/Zenith-7B-dpo")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```

## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer