README.md

Quantization made by Richard Erkhov.

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

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

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


vortex-3b-v2 - GGUF
- Model creator: https://huggingface.co/OEvortex/
- Original model: https://huggingface.co/OEvortex/vortex-3b-v2/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [vortex-3b-v2.Q2_K.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q2_K.gguf) | Q2_K | 1.01GB |
| [vortex-3b-v2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.IQ3_XS.gguf) | IQ3_XS | 1.14GB |
| [vortex-3b-v2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.IQ3_S.gguf) | IQ3_S | 1.16GB |
| [vortex-3b-v2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q3_K_S.gguf) | Q3_K_S | 1.16GB |
| [vortex-3b-v2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.IQ3_M.gguf) | IQ3_M | 1.28GB |
| [vortex-3b-v2.Q3_K.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q3_K.gguf) | Q3_K | 1.38GB |
| [vortex-3b-v2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q3_K_M.gguf) | Q3_K_M | 1.38GB |
| [vortex-3b-v2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q3_K_L.gguf) | Q3_K_L | 1.49GB |
| [vortex-3b-v2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.IQ4_XS.gguf) | IQ4_XS | 1.43GB |
| [vortex-3b-v2.Q4_0.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q4_0.gguf) | Q4_0 | 1.49GB |
| [vortex-3b-v2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.IQ4_NL.gguf) | IQ4_NL | 1.5GB |
| [vortex-3b-v2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q4_K_S.gguf) | Q4_K_S | 1.5GB |
| [vortex-3b-v2.Q4_K.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q4_K.gguf) | Q4_K | 1.66GB |
| [vortex-3b-v2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q4_K_M.gguf) | Q4_K_M | 1.66GB |
| [vortex-3b-v2.Q4_1.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q4_1.gguf) | Q4_1 | 1.64GB |
| [vortex-3b-v2.Q5_0.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q5_0.gguf) | Q5_0 | 1.8GB |
| [vortex-3b-v2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q5_K_S.gguf) | Q5_K_S | 1.8GB |
| [vortex-3b-v2.Q5_K.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q5_K.gguf) | Q5_K | 1.93GB |
| [vortex-3b-v2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q5_K_M.gguf) | Q5_K_M | 1.93GB |
| [vortex-3b-v2.Q5_1.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q5_1.gguf) | Q5_1 | 1.95GB |
| [vortex-3b-v2.Q6_K.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q6_K.gguf) | Q6_K | 2.12GB |
| [vortex-3b-v2.Q8_0.gguf](https://huggingface.co/RichardErkhov/OEvortex_-_vortex-3b-v2-gguf/blob/main/vortex-3b-v2.Q8_0.gguf) | Q8_0 | 2.75GB |




Original model description:
---
language:
- en
license: other
tags:
- HelpingAI
- vortex
datasets:
- OEvortex/uncensored-vortex
license_name: hsul
license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
pipeline_tag: text-generation
model-index:
- name: vortex-3b-v2
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 39.68
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 65.04
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 25.09
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 33.8
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 59.12
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 2.05
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
      name: Open LLM Leaderboard
---
![Vortex 3b](https://cdn-lfs-us-1.huggingface.co/repos/68/cb/68cb18839210e9d774c72c739ef72fb95cb03f6f857e6b5a2377406f2078e65a/04b4c8104a551ec9754fd1169842ee67c06ced0fb16569b5fca804c2068578e9?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27vortex%25203b.png%3B+filename%3D%22vortex+3b.png%22%3B&response-content-type=image%2Fpng&Expires=1711282309&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxMTI4MjMwOX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzY4L2NiLzY4Y2IxODgzOTIxMGU5ZDc3NGM3MmM3MzllZjcyZmI5NWNiMDNmNmY4NTdlNmI1YTIzNzc0MDZmMjA3OGU2NWEvMDRiNGM4MTA0YTU1MWVjOTc1NGZkMTE2OTg0MmVlNjdjMDZjZWQwZmIxNjU2OWI1ZmNhODA0YzIwNjg1NzhlOT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=T0d7vhvs9DjdMClzOOEyJMVe4e33u7A-9VTvApC3lMQgW7GXt-hOACXDWDp2TQMv6WoxL7DmGBh-d2uXvGT-2Sqx%7EUcce2pxq1yqtkMEi7sf2WYSHtmaXrIWAiVF%7EPeidG1wRr8wfUY3qIjlKtMVJs7RGbzvAgyvhscazuqutIj37tlIjEcYUXYOuYZoqA3OhoXfpiawCvmXc%7EAul-bAWwAYx91BWvGw9fw4tv20wisJDsh6BV7HEWnV%7EYbXvCxxlZZ4BbcWrYDN%7EMRf48EElCacf5KMpDMbCa52rO-ZvXCWgap%7EzUaIemRSQ84rpgTlVKb--D3GL3pUwRroaiRF7A__&Key-Pair-Id=KCD77M1F0VK2B)
**Model Overview**

Vortex-3b-v2 is an upgraded version of the Vortex-3b model ie. a 2.78 billion parameter causal language model created by OEvortex that was derived from EleutherAI's Pythia-2.8b and trained on 79% of uncensored-vortex dataset

```python
from transformers import pipeline

# Initialize the pipeline
pipe = pipeline("text-generation", model="OEvortex/vortex-3b-v2")

# Use the pipeline
text = "Once upon a time"
generated_text = pipe(text, max_length=100, do_sample=True)[0]['generated_text']

print(generated_text)
```

```python
# Use a pipeline as a high-level helper
from transformers import pipeline

text = pipeline(model="OEvortex/vortex-3b-v2", torch_dtype=torch.bfloat16, device_map="auto")

res = text("Explain to me the difference between nuclear fission and fusion.")
print(res[0]["text"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OEvortex__vortex-3b-v2)
| Metric | vortex 3b | vortex 3b-v2 | dolly-v2-3b | pythia-2.8b-deduped |
|---------|----------:|-------------:|------------------:|----------------------------------:|
| Avg.    | 35.76     | 37.46        | 25.26             | 36.72                             |
| AI2 Reasoning Challenge (25-Shot) | 31.91 | 39.68 | 22.83 | 36.26 |
| HellaSwag (10-Shot) | 56.89 | 65.04 | 26.55 | 60.66 |
| MMLU (5-Shot) | 27.32 | 25.09 | 24.7 | 26.78 |
| TruthfulQA (0-shot) | 37.39 | 33.80 |       0            | 35.56 |
| Winogrande (5-shot) | 60.14 | 59.12 | 59.43 | 60.22 |
| GSM8k (5-shot) | 0.91 | 2.05 | 1.86 | 0.83 |