75 lines
3.4 KiB
Markdown
75 lines
3.4 KiB
Markdown
---
|
|
base_model: Felladrin/llama2_xs_460M_experimental_platypus
|
|
datasets:
|
|
- garage-bAInd/Open-Platypus
|
|
- Felladrin/Open-Platypus-train.csv
|
|
inference: false
|
|
model_creator: Felladrin
|
|
model_name: llama2_xs_460M_experimental_platypus
|
|
pipeline_tag: text-generation
|
|
quantized_by: afrideva
|
|
tags:
|
|
- gguf
|
|
- ggml
|
|
- quantized
|
|
- q2_k
|
|
- q3_k_m
|
|
- q4_k_m
|
|
- q5_k_m
|
|
- q6_k
|
|
- q8_0
|
|
widget:
|
|
- text: '### User:
|
|
|
|
How do the characteristics of our solar system compare to other known planetary
|
|
systems?
|
|
|
|
### Assistant:'
|
|
- text: '### User:
|
|
|
|
Which scientist is best known for his theory of relativity and the equation E=mc²?
|
|
|
|
### Assistant:'
|
|
- text: '### User:
|
|
|
|
Write a 5 paragraph-long story about a girl called Alice.
|
|
|
|
### Assistant:'
|
|
- text: '### User:
|
|
|
|
What chemical element, known for its ability to conduct electricity and heat,
|
|
is also the most abundant metal in Earth''''s crust?
|
|
|
|
### Assistant:'
|
|
---
|
|
# Felladrin/llama2_xs_460M_experimental_platypus-GGUF
|
|
|
|
Quantized GGUF model files for [llama2_xs_460M_experimental_platypus](https://huggingface.co/Felladrin/llama2_xs_460M_experimental_platypus) from [Felladrin](https://huggingface.co/Felladrin)
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [llama2_xs_460m_experimental_platypus.fp16.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.fp16.gguf) | fp16 | 925.26 MB |
|
|
| [llama2_xs_460m_experimental_platypus.q2_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.q2_k.gguf) | q2_k | 212.50 MB |
|
|
| [llama2_xs_460m_experimental_platypus.q3_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.q3_k_m.gguf) | q3_k_m | 238.81 MB |
|
|
| [llama2_xs_460m_experimental_platypus.q4_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.q4_k_m.gguf) | q4_k_m | 288.45 MB |
|
|
| [llama2_xs_460m_experimental_platypus.q5_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.q5_k_m.gguf) | q5_k_m | 333.22 MB |
|
|
| [llama2_xs_460m_experimental_platypus.q6_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.q6_k.gguf) | q6_k | 380.79 MB |
|
|
| [llama2_xs_460m_experimental_platypus.q8_0.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental_platypus-GGUF/resolve/main/llama2_xs_460m_experimental_platypus.q8_0.gguf) | q8_0 | 492.57 MB |
|
|
|
|
|
|
|
|
## Original Model Card:
|
|
# ahxt's llama2_xs_460M_experimental trained on the Open-Platypus dataset
|
|
|
|
- Base model: [ahxt/llama2_xs_460M_experimental](https://huggingface.co/ahxt/llama2_xs_460M_experimental)
|
|
- Dataset: [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus)
|
|
- Trained with [AutoTrain Advanced](https://github.com/huggingface/autotrain-advanced) using [these parameters](https://huggingface.co/Felladrin/llama2_xs_460M_experimental_platypus/blob/0ea9d942179b0d1905b28e0b0befff855720aa8d/training_params.json) and [this CSV file](https://huggingface.co/datasets/Felladrin/Open-Platypus-train.csv/blob/main/train.csv)
|
|
|
|
## Recommended Prompt Format
|
|
|
|
```
|
|
### User:
|
|
<message>
|
|
### Assistant:
|
|
``` |