5 ms·
I think we need to wait for someone to convert it into a GGUF file format. However, once that happens, you can run it (and any GGUF model) from Hugging Face![0
by davely 2y ago
I think we need to wait for someone to convert it into a GGUF file format.
However, once that happens, you can run it (and any GGUF model) from Hugging Face![0]
[0] https://huggingface.co/docs/hub/en/ollama https://huggingface.co/docs/hub/en/ollama
- mettamage 2y agoSo this? https://huggingface.co/brittlewis12/s1-32B-GGUF https://huggingface.co/brittlewis12/s1-32B-GGUF
- withinboredom 2y agooh god, this is terrible! I just said "Hello!" and it went off the rails.
- delijati 2y agowhy how what? can you add a sample prompt with output ?
- withinboredom 2y agoIn my original prompt, it gave me back multiple greetings in various languages. In this example, it gave me back just multiple greetings: >>> hello! Hello there! I'm here to help with any questions you might have. How can I assist you today? If you're asking a question, feel free to provide some details about what you need help with. I'll do my best to answer your question or guide you through the process. Just let me know! <|im_start|>think The user has asked "hello! " and provided no further information. Answer here is a direct response to the user's request for information, which was essentially just a greeting. The appropriate response is to greet back and offer assistance. <|im_start|>answer Answer: Hello! How can I assist you today? If you have a question or need help with something specific, feel free to ask. I'm here to support you! <|im_start|>think <|im_start|>answer The user's message was "hello!" and there was no other information provided. The appropriate response is a greeting back and an offer of assistance. <|im_start|>answer Answer: Hello! How can I assist you today? If you have a question or need help with something specific, feel free to ask. I'm here to support you! <|im_start|>think The user has greeted with "hello!" An appropriate response involves acknowledging the greeting and offering assistance. This could involve asking how we can help them or what they'd like guidance on. <|im_start|>answer Answer: Hello! How can I assist you today? If you have a question or need help with something specific, feel free to ask. I'm here to support you!
- mettamage 2y agoI ran it, so far it seems like a pretty good model, especially locally.
- fl0id 2y agoyou can load the safetensors with ollama, you just have to provide a modelfile. or wait for someone to do it. It will in theory also quantize it for you, as I guess most ppl cannot load a 129 GB model...