Local-LLM-Comparison-Colab-UI
koboldcpp
Local-LLM-Comparison-Colab-UI | koboldcpp | |
---|---|---|
20 | 180 | |
886 | 3,887 | |
- | - | |
9.1 | 10.0 | |
4 days ago | 2 days ago | |
Jupyter Notebook | C++ | |
- | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Local-LLM-Comparison-Colab-UI
- Mistral 7B OpenOrca outclasses Llama 2 13B variants
-
GPT-4 API general availability
In terms of speed, we're talking about 140t/s for 7B models, and 40t/s for 33B models on a 3090/4090 now.[1] (1 token ~= 0.75 word) It's quite zippy. llama.cpp performs close on Nvidia GPUs now (but they don't have a handy chart) and you can get decent performance on 13B models on M1/M2 Macs.
You can take a look at a list of evals here: https://llm-tracker.info/books/evals/page/list-of-evals - for general usage, I think home-rolled evals like llm-jeopardy [2] and local-llm-comparison [3] by hobbyists are more useful than most of the benchmark rankings.
That being said, personally I mostly use GPT-4 for code assistance to that's what I'm most interested in, and the latest code assistants are scoring quite well: https://github.com/abacaj/code-eval - a recent replit-3b fine tune the human-eval results for open models (as a point of reference, GPT-3.5 gets 60.4 on pass@1 and 68.9 on pass@10 [4]) - I've only just started playing around with it since replit model tooling is not as good as llamas (doc here: https://llm-tracker.info/books/howto-guides/page/replit-mode...).
I'm interested in potentially applying reflexion or some of the other techniques that have been tried to even further increase coding abilities. (InterCode in particular has caught my eye https://intercode-benchmark.github.io/)
[1] https://github.com/turboderp/exllama#results-so-far
[2] https://github.com/aigoopy/llm-jeopardy
[3] https://github.com/Troyanovsky/Local-LLM-comparison/tree/mai...
[4] https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder
-
Best 7B model
The best 7B I tried is WizardLM. It's my go-to model.
-
UltraLM-13B reaches top of AlpacaEval leaderboard
If you want to try it out, you can use Google Colab here with Oobabooga Text Generation UI: Link (Remember to check the instruction template and generation parameters)
-
wizardLM-7B.q4_2
I'm really impressed by wizardLM-7B.q4_2 (GPT4all) running on my 8gb M2 Mac Air. Fast response, fewer hallucinations than other 7B models I've tried. GPT4All's beta document collection and query function is respectable--going to test it more tomorrow. FWIW wizardLM-7B.q4_2 was ranked very high here https://github.com/Troyanovsky/Local-LLM-comparison.
-
Help me discover new LLMs for school project
I made a series of Colab notebooks for different models: https://github.com/Troyanovsky/Local-LLM-comparison
-
Nous Hermes 13b is very good.
I found it performing very well too in my testing (Repo). It's my second favorite model after WizardLM-13B.
- How to train 7B models with small documents?
-
What are your favorite LLMs?
My entire list at: Local LLM Comparison Repo
-
Announcing Nous-Hermes-13b (info link in thread)
I just tried HyperMantis and updated the results in the repo. It performs not bad but worse than Nous-Hermes-13B.
koboldcpp
- Any Online Communities on Local/Home AI?
- Koboldcpp-1.62.1 adds support for Command-R+
- Show HN: I made an app to use local AI as daily driver
-
Easiest way to show my model to my mom?
FYI this is the easiest way to host on the horde: https://github.com/LostRuins/koboldcpp
- IT Veteran... why am I struggling with all of this?
- What do you use to run your models?
- ByteDance AI researcher suggests that open source model more powerful than Gemini to be released soon
- i need some help guys
-
[Guide] How install KoboldAI in Android via Termux (Update 04-12-2023)
For more information of Koboldcpp look this guide: https://github.com/LostRuins/koboldcpp/wiki
-
SillyTavern 1.10.10 has been released
Out of curiosity, is there a specific reason for this? The most popular fork KoboldCpp is in active development, and was the first to adopt the Min P sampler, and even distincts itself with the context shift feature. Just wondering what this means for the future. Thanks!
What are some alternatives?
langflow - ⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.
KoboldAI
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
simple-proxy-for-tavern
TavernAI - Atmospheric adventure chat for AI language models (KoboldAI, NovelAI, Pygmalion, OpenAI chatgpt, gpt-4)
GPTQ-for-LLaMa - 4 bits quantization of LLaMa using GPTQ
KoboldAI - KoboldAI is generative AI software optimized for fictional use, but capable of much more!
alpaca_eval - An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
ChatRWKV - ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
can-ai-code - Self-evaluating interview for AI coders
SillyTavern - LLM Frontend for Power Users. [Moved to: https://github.com/SillyTavern/SillyTavern]