---
license: apache-2.0
datasets:
- totally-not-an-llm/sharegpt-hyperfiltered-3k
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# Puma-3B - GGUF
- Model creator: [acrastt](https://huggingface.co/acrastt)
- Original model: [Puma-3B](https://huggingface.co/acrastt/Puma-3B)
OpenLlama is a free reimplementation of the original Llama Model which is licensed under Apache 2 license.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
This is [OpenLLaMA 3B V2](https://huggingface.co/openlm-research/open_llama_3b_v2) finetuned on [ShareGPT Hyperfiltered](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k) for 1 epochs.
Prompt template:
```
### HUMAN:
{prompt}
### RESPONSE:
```
GGML quants available [here](https://huggingface.co/TheBloke/Puma-3b-GGML).
GPTQ quants available [here](https://huggingface.co/TheBloke/Puma-3b-GPTQ).
Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please!
# [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_acrastt__Puma-3B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 35.93 |
| ARC (25-shot) | 41.3 |
| HellaSwag (10-shot) | 71.85 |
| MMLU (5-shot) | 27.51 |
| TruthfulQA (0-shot) | 38.34 |
| Winogrande (5-shot) | 66.38 |
| GSM8K (5-shot) | 0.76 |
| DROP (3-shot) | 5.38 |
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)