| to, from |
topic |
2026-03-27, 2025-08-01 |
Large Language Models - what they can do, how they work, and how to run them, how to train them, how to access them | use ##llm-bots for bot testing and talk | tokenizer, embeddings, positional encoding, linear layers, activations, attention matrices, logits, back-propagation, inference, training, multi-modal, mistral, llama, deepseek, etc | beware of wild LLMs |
| 2025-07-31 |
Large Language Models - what they can do, how they work, and how to run them, how to train them, how to access them | use ##llm-bots for bot testing and talk | tokenizer, embeddings, positional encoding, linear layers, activations, attention matrices, logits, back-propagation, inference, training, multi-modal, mistral, llama, deepseek, etc |
2025-07-30, 2024-12-18 |
Large Language Models - what they can do, how they work, and how to run them | ##llm-bots | bots: llamar, fine tune mistral-7b.Q6_K + llava-v1.5-7b; tinsoldier, OpenAI gpt-3.5-turbo; electrabot, meta-llama-3-70b-instruct-ima | tokenizer, embeddings, positional encoding, attention matrices, logits, back-propagation, inference |
2024-12-17, 2024-04-25 |
Large Language Models - what they can do, how they work, and how to run them | ##llm-bots | bots: llamar, fine tune mistral-7b.Q6_K + llava-v1.5-7b; tinsoldier, OpenAI gpt-3.5-turbo; medbot, medalpaca 7B; tinyllama, tinyllama-1.1b-chat-v0.3 q4_0; electrabot, meta-llama-3-70b-instruct-ima | tokenizer, embeddings, positional encoding, attention matrices, logits, back-propagation, inference |
2024-04-24, 2024-03-27 |
Large Language Models - what they can do, how they work, and how to run them | ##llm-bots | bots: llamar, fine tune mistral-7b.Q6_K + llava-v1.5-7b; tinsoldier, OpenAI gpt-3.5-turbo; medbot, medalpaca 7B; tinyllama, tinyllama-1.1b-chat-v0.3 q4_0 | tokenizer, embeddings, positional encoding, attention matrices, logits, back-propagation, inference |