Live data from Hacker News

Codestral Mamba

mistral.ai

111–120 of 148 posts

Re: Codestral Mamba

#111

I know it's just a throwaway line, but the bit about Cleopatra at the top feels in poor taste. It's completely inaccurate in that no one has ever attributed her death to a "mamba", and even the asp that some sources claim has been disputed. But even aside from that, it just feels weird that a human being's death has turned into a random reference you can make in a throwaway joke while advertising a product. They're c…

I do agree, but there’s worse.

Ever heard of Patrice Lumumba? He was a congolese politician involved in its independence and democratization. He was shot with the involvement of western forces. There’s a drink named after him: Hot chocolate with a shot of rum.

Re: Codestral Mamba

#112
I kinda just want something that can keep up with the original version of Copilot. It was so much better than the crap they’re pumping out now (keeps messing up syntax and only completing a few characters at a time).

Re: Codestral Mamba

#113

Does anyone have a favorite FIM capable model? I've been using codellama-13b through ollama w/ a vim extension i wrote and it's okay but not amazing, I definitely get better code most of the time out of Gemma-27b but no FIM (and for some reason codellama-34b has broken inference for me)

Is the extension you wrote public?

Re: Codestral Mamba

#114
post #8

What are the steps required to get this running in VS Code? If they had linked to the instructions in their post (or better yet a link to a one click install of a VS Code Extension), it would help a lot with adoption. (BTW I consider it malpractice that they are at the top of hacker news with a model that is of great interest to a large portion of the users where and they do not have a monetizable call to action on t…

Website codegpt.co also has a plugin for both VS Code and Intellij. When model becomes available in Ollama, you can connect plugin in VS code to local ollama instance.

Re: Codestral Mamba

#115

Does anyone have a favorite FIM capable model? I've been using codellama-13b through ollama w/ a vim extension i wrote and it's okay but not amazing, I definitely get better code most of the time out of Gemma-27b but no FIM (and for some reason codellama-34b has broken inference for me)

Is the extension you wrote public?

no but it's super super janky and simple hodgepode of stack overflow and gemma:27b generated code, i'll just put it in the comment here, you just need CURL on your path and vim that's compiled with some specific flag

    function! GetSurroundingLines(n)
        let l:current_line = line('.')
        let l:start_line = max([1, l:current_line - a:n])
        let l:end_line = min([line('$'), l:current_line + a:n])
        
        let l:lines_before = getline(l:start_line, l:current_line - 1)
        let l:lines_after = getline(l:current_line + 1, l:end_line)
        
        return [l:lines_before, l:lines_after]
    endfunction
    
    function! AIComplete()
        let l:n = 256
        let [l:lines_before, l:lines_after] = GetSurroundingLines(l:n)
        
        let l:prompt = '
' . join(l:lines_before, "\n") . ' ' . join(l:lines_after, "\n") . ' '
        
        let l:json_data = json_encode({
            \ 'model': 'codellama:13b-code-q6_K',
            \ 'keep_alive': '30m',
            \ 'stream': v:false,
            \ 'prompt': l:prompt
        \ })
        
        let l:response = system('curl -s -X POST -H "Content-Type: application/json" -d ' . shellescape(l:json_data) . ' http://localhost:11434/api/generate')
    
        let l:completion = json_decode(l:response)['response']
        let l:paste_mode = &paste
        set paste
        execute "normal! a" . l:completion
        let &paste = l:paste_mode
    endfunction
    
    nnoremap c :call AIComplete()

Re: Codestral Mamba

#116

I kinda just want something that can keep up with the original version of Copilot. It was so much better than the crap they’re pumping out now (keeps messing up syntax and only completing a few characters at a time).

Have you tried supermaven? It replaced copilot for me a couple of months ago.

Re: Codestral Mamba

#117

I kinda just want something that can keep up with the original version of Copilot. It was so much better than the crap they’re pumping out now (keeps messing up syntax and only completing a few characters at a time).

Have you tried supermaven? (https://supermaven.com). I find it much better than copilot. Using it daily.

Re: Codestral Mamba

#118

Earlier quoted context omitted.

Is the extension you wrote public?

no but it's super super janky and simple hodgepode of stack overflow and gemma:27b generated code, i'll just put it in the comment here, you just need CURL on your path and vim that's compiled with some specific flag function! GetSurroundingLines(n) let l:current_line = line('.') let l:start_line = max([1, l:current_line - a:n]) let l:end_line = min([line('$'), l:current_line + a:n]) let l:lines_before = getline(l:st…

Thanks!

Re: Codestral Mamba

#119
post #116

I kinda just want something that can keep up with the original version of Copilot. It was so much better than the crap they’re pumping out now (keeps messing up syntax and only completing a few characters at a time).

Have you tried supermaven? It replaced copilot for me a couple of months ago.

I tried it, uses GPT-4o, the $10 sign up credit dissapeared in a few hours of intense coding, I'm not paying $500/mo for a fancy autocomple. Manual instruct style chat about code with Claude-Sonnet-3.5 is the best price/perf I've tried so far, through poe.com I use around 30k credits per day of coding of the 1M monthly allotment, I think it was $200/y. It's not available directly in my country. I've tried a bunch of local models too but Claude is just next level and inference is very cheap.

Re: Codestral Mamba

#120

> Unlike Transformer models, Mamba models offer the advantage of linear time inference and the theoretical ability to model sequences of infinite length > We have tested Codestral Mamba on in-context retrieval capabilities up to 256k tokens Why only 256k tokens? Gemini's context window is 1 million or more and it's (probably) not even using Mamba.

Gemini is probably using ring attention. But scaling to that size requires more engineering effort in terms of interlink that goes beyond the purpose of this release from Mistral.
Post reply on HN