base_model, datasets, inference, language, license, model_creator, model_name, pipeline_tag, quantized_by, tags, widget

base_model	datasets	inference	language	license	model_creator	model_name	pipeline_tag	quantized_by	tags	widget
Felladrin/Smol-Llama-101M-Chat-v1	Open-Orca/SlimOrca-Dedup VMware/open-instruct LDJnr/Capybara cognitivecomputations/ultrachat-uncensored starfishmedical/webGPT_x_dolly THUDM/webglm-qa	false	en	apache-2.0	Felladrin	Smol-Llama-101M-Chat-v1	text-generation	afrideva	text-generation gguf ggml quantized q2_k q3_k_m q4_k_m q5_k_m q6_k q8_0	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

Felladrin/Smol-Llama-101M-Chat-v1-GGUF

Quantized GGUF model files for Smol-Llama-101M-Chat-v1 from Felladrin

Name	Quant method	Size
smol-llama-101m-chat-v1.fp16.gguf	fp16	204.25 MB
smol-llama-101m-chat-v1.q2_k.gguf	q2_k	51.90 MB
smol-llama-101m-chat-v1.q3_k_m.gguf	q3_k_m	58.04 MB
smol-llama-101m-chat-v1.q4_k_m.gguf	q4_k_m	66.38 MB
smol-llama-101m-chat-v1.q5_k_m.gguf	q5_k_m	75.31 MB
smol-llama-101m-chat-v1.q6_k.gguf	q6_k	84.80 MB
smol-llama-101m-chat-v1.q8_0.gguf	q8_0	109.33 MB

Original Model Card:

A Llama Chat Model of 101M Parameters

• 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
• Availability in other ML formats:
  • ONNX: Felladrin/onnx-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 prefer using contrastive search for inference:

add_special_tokens: true
penalty_alpha: 0.5
top_k: 5