100 lines
5.9 KiB
Markdown
100 lines
5.9 KiB
Markdown
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-v1 - GGUF
|
|
- Model creator: https://huggingface.co/Xenon1/
|
|
- Original model: https://huggingface.co/Xenon1/Zenith-7B-dpo-v1/
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [Zenith-7B-dpo-v1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q2_K.gguf) | Q2_K | 2.53GB |
|
|
| [Zenith-7B-dpo-v1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
|
|
| [Zenith-7B-dpo-v1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.IQ3_S.gguf) | IQ3_S | 2.96GB |
|
|
| [Zenith-7B-dpo-v1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
|
|
| [Zenith-7B-dpo-v1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.IQ3_M.gguf) | IQ3_M | 3.06GB |
|
|
| [Zenith-7B-dpo-v1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q3_K.gguf) | Q3_K | 3.28GB |
|
|
| [Zenith-7B-dpo-v1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
|
|
| [Zenith-7B-dpo-v1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
|
|
| [Zenith-7B-dpo-v1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
|
|
| [Zenith-7B-dpo-v1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q4_0.gguf) | Q4_0 | 3.83GB |
|
|
| [Zenith-7B-dpo-v1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
|
|
| [Zenith-7B-dpo-v1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
|
|
| [Zenith-7B-dpo-v1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q4_K.gguf) | Q4_K | 4.07GB |
|
|
| [Zenith-7B-dpo-v1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
|
|
| [Zenith-7B-dpo-v1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q4_1.gguf) | Q4_1 | 4.24GB |
|
|
| [Zenith-7B-dpo-v1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q5_0.gguf) | Q5_0 | 4.65GB |
|
|
| [Zenith-7B-dpo-v1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
|
|
| [Zenith-7B-dpo-v1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q5_K.gguf) | Q5_K | 4.78GB |
|
|
| [Zenith-7B-dpo-v1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
|
|
| [Zenith-7B-dpo-v1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q5_1.gguf) | Q5_1 | 5.07GB |
|
|
| [Zenith-7B-dpo-v1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q6_K.gguf) | Q6_K | 5.53GB |
|
|
| [Zenith-7B-dpo-v1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Xenon1_-_Zenith-7B-dpo-v1-gguf/blob/main/Zenith-7B-dpo-v1.Q8_0.gguf) | Q8_0 | 7.17GB |
|
|
|
|
|
|
|
|
|
|
Original model description:
|
|
---
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
tags:
|
|
- mistral
|
|
- Zenith-7B-dpo-v1
|
|
pipeline_tag: text-generation
|
|
---
|
|
# Model Card for Zenith-7B-dpo-v1
|
|
|
|
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).
|
|
|
|
## 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-v1")
|
|
tokenizer = AutoTokenizer.from_pretrained("Xenon1/Zenith-7B-dpo-v1")
|
|
|
|
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
|
|
|