mergekit
garnet
mergekit | garnet | |
---|---|---|
6 | 4 | |
3,521 | 9,326 | |
18.7% | 26.8% | |
9.2 | 9.3 | |
6 days ago | 3 days ago | |
Python | C# | |
GNU Lesser General Public License v3.0 only | MIT License |
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.
mergekit
-
Language Models Are Super Mario: Absorbing Abilities from Homologous Models
For others like me who’d not heard of merging before, this seems to be one tool[0] (there may be others)
[0] https://github.com/arcee-ai/mergekit
- FLaNK AI Weekly 25 March 2025
- Tools for merging pretrained large language models
-
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
mergekit is the tool you need to do this
https://github.com/cg123/mergekit
-
Iambe-RP-20b: An uncensored L2 Frankenstein model directly trained with RP-oriented cDPO
I actually asked the creator of mergekit a question here. In his response, I learned how to use task_arithmetic to isolate the deltas. One could, in theory, use WANDA on that model from the second example, then merge it back into another model. However, that's firmly past the frontier of what has been tried, so experimentation might be messy.
-
LLMs cannot find reasoning errors, but can correct them
Ah, actually reviewing that more closely I found a link to it in the acknowledgements.
https://github.com/cg123/mergekit
garnet
-
A MySQL compatible database engine written in pure Go
You would be surprised by performance of modern .NET :)
Writing no-alloc is oftentimes done by reducing complexity and not doing "stupid" tricks that actually work against JIT and CoreLib features.
For databases specifically, .NET is actually positioned very well with its low-level features (intrisics incl. SIMD, FFI, struct generics though not entirely low-level) and high-throughput GC.
Interesting example of this applied in practice is Garnet[0]/FASTER[1]. Keep in mind that its codebase still consist of un-idiomatic C# and you can do way better by further simplification, but it already does the job well enough.
[0] https://github.com/microsoft/garnet
[1] https://github.com/microsoft/FASTER
- FLaNK AI Weekly 25 March 2025
-
Redis License Changed
At the same time Microsoft releases Garnet: https://github.com/microsoft/garnet
Good timing.
- Garnet – A new remote cache-store from Microsoft Research
What are some alternatives?
Finetune_LLMs - Repo for fine-tuning Casual LLMs
redis - Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes
xTuring - Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
KeyDB - A Multithreaded Fork of Redis
LLMLingua - To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
FASTER - Fast persistent recoverable log and key-value store + cache, in C# and C++.
task_vectors - Editing Models with Task Arithmetic
dragonfly - A modern replacement for Redis and Memcached
difftastic - a structural diff that understands syntax 🟥🟩
FLiPStackWeekly - FLaNK AI Weekly covering Apache NiFi, Apache Flink, Apache Kafka, Apache Spark, Apache Iceberg, Apache Ozone, Apache Pulsar, and more...
makeMoE - From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
deeplake - Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai