File size: 5,337 Bytes
c36152d c360bdf 6423679 c360bdf 697456e c360bdf c36152d c360bdf 1036205 b7c10b0 1036205 fd57078 c360bdf b7c10b0 c360bdf 697456e c360bdf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
---
license: apache-2.0
language:
- en
tags:
- text-generation
base_model: BEE-spoke-data/smol_llama-101M-GQA
datasets:
- Open-Orca/SlimOrca-Dedup
- VMware/open-instruct
- LDJnr/Capybara
- cognitivecomputations/ultrachat-uncensored
- starfishmedical/webGPT_x_dolly
- THUDM/webglm-qa
widget:
- text: |-
<|im_start|>system
You are a helpful assistant who gives creative responses.<|im_end|>
<|im_start|>user
Write the background story of a game about wizards and llamas in a sci-fi world.<|im_end|>
<|im_start|>assistant
- text: |-
<|im_start|>system
A friendly chat between a user and an assistant.<|im_end|>
<|im_start|>user
Got a question for you!<|im_end|>
<|im_start|>assistant
Sure! What's it?<|im_end|>
<|im_start|>user
I need to build a simple website. Where should I start learning about web development?<|im_end|>
<|im_start|>assistant
- text: |-
<|im_start|>system
You are a helpful assistant who provides concise answers to the user's questions.<|im_end|>
<|im_start|>user
How to become more healthy?<|im_end|>
<|im_start|>assistant
- text: |-
<|im_start|>system
You are a helpful assistant, who always answers with empathy.<|im_end|>
<|im_start|>user
List the pros and cons of social media.<|im_end|>
<|im_start|>assistant
- text: |-
<|im_start|>system
You are a helpful assistant, who always answers with empathy.<|im_end|>
<|im_start|>user
Hello!<|im_end|>
<|im_start|>assistant
Hi! How can I help you today?<|im_end|>
<|im_start|>user
Take a look at the info below.
- The tape inside the VHS cassettes is very delicate and can be easily ruined, making them unplayable and unrepairable. The reason the tape deteriorates is that the magnetic charge needed for them to work is not permanent, and the magnetic particles end up losing their charge in a process known as remanence decay. These particles could also become demagnetised via being stored too close to a magnetic source.
- One of the most significant issues with VHS tapes is that they have moving parts, meaning that there are more occasions when something can go wrong, damaging your footage or preventing it from playing back. The tape itself is a prominent cause of this, and tape slippage can occur. Tapes slippage can be caused when the tape loses its tension, or it has become warped. These problems can occur in storage due to high temperatures or frequent changes in humidity.
- VHS tapes deteriorate over time from infrequent or overuse. Neglect means mold and dirt, while overuse can lead to scratches and technical difficulties. This is why old VHS tapes inevitably experience malfunctions after a long period of time. Usually anywhere between 10 to 25+ years.
- Some VHS tapes like newer mini DVs and Digital 8 tapes can suffer from digital corruption, meaning that the footage becomes lost and cannot be recovered. These tapes were the steppingstone from VHS to the digital age when capturing footage straight to digital became the norm. Unfortunately,they are susceptible to digital corruption, which causes video pixilation and/or loss of audio.<|im_end|>
<|im_start|>assistant
Alright!<|im_end|>
<|im_start|>user
Now I'm going to write my question, and if the info above is useful, you can use them in your response.
Ready?<|im_end|>
<|im_start|>assistant
Ready for your question!<|im_end|>
<|im_start|>user
Why do VHS tapes deteriorate over time?<|im_end|>
<|im_start|>assistant
inference:
parameters:
add_special_tokens: true
max_new_tokens: 250
penalty_alpha: 0.5
top_k: 5
---
# A Llama Chat Model of 101M Parameters
- Base model: [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA)
- Datasets:
- [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
- [VMware/open-instruct](https://huggingface.co/datasets/VMware/open-instruct)
- [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capybara)
- [cognitivecomputations/ultrachat-uncensored](https://huggingface.co/datasets/cognitivecomputations/ultrachat-uncensored)
- [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly)
- [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
- Availability in other ML formats:
- GGUF: [afrideva/Smol-Llama-101M-Chat-v1-GGUF](https://huggingface.co/afrideva/Smol-Llama-101M-Chat-v1-GGUF)
- ONNX: [Felladrin/onnx-Smol-Llama-101M-Chat-v1](https://huggingface.co/Felladrin/onnx-Smol-Llama-101M-Chat-v1)
- MLC: [Felladrin/mlc-q4f16-Smol-Llama-101M-Chat-v1](https://huggingface.co/Felladrin/mlc-q4f16-Smol-Llama-101M-Chat-v1)
## Recommended Prompt Format
The recommended prompt format is as follows:
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
```
## Recommended Inference Parameters
To get the best results, add special tokens and use [contrastive search](https://huggingface.co/docs/transformers/main/en/generation_strategies#contrastive-search):
```yml
add_special_tokens: true
penalty_alpha: 0.5
top_k: 5
```
|