Alternatives
Products that do what Local fine tuning for Mistral and SDXL, GPU mem/latency optimization does
100% bootstrapped new startup. It lets you fine tune Mistral-7B and SDXL. In particular, for the LLM fine tuning we implemented a dataprep pipeline that turns websites/pdfs/doc files into question-answer pairs for training the small LLM using an big LLM. It includes a GPU scheduler that can do finegrained GPU memory scheduling (Kubernetes can only do whole-GPU, we do it per-GB of GPU memory to pack both inference and fine tuning jobs into the same fleet) to fit model instances into GPU memory to optimally trade off user facing latency with GPU memory utilization It's a pretty…
- 1FL
I've been playing around with https://github.com/zphang/minimal-llama/ and https://github.com/tloen/alpaca-lora/blob/main/finetune.py, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU. To prepare the data, simply separate your text with two blank lines. There's an inference tab, so you can test how the tuned model behaves. This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio. Enjoy!
2023 · github.com
- 2FT
Aug 2026 · github.com
- 38F
Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA / LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…
2023 · github.com
- 4TL
Hey HN, we wanted to share our repo where we fine-tuned Llama 3.1 on Google TPUs. We’re building AI infra to fine-tune and serve LLMs on non-NVIDIA GPUs (TPUs, Trainium, AMD GPUs). The problem: Right now, 90% of LLM workloads run on NVIDIA GPUs, but there are equally powerful and more cost-effective alternatives out there. For example, training and serving Llama 3.1 on Google TPUs is about 30% cheaper than NVIDIA GPUs. But developer tooling for non-NVIDIA chipsets is lacking. We felt this pain ourselves. We initially tried using PyTorch XLA to train Llama 3.1 on TPUs, but it was rough: xla…
2024 · github.com
- 5FA
Hey HN! We’re building FinetuneDB (https://finetunedb.com/), an LLM fine-tuning platform. It enables teams to easily create and manage high-quality datasets, and streamlines the entire workflow from fine-tuning to serving and evaluating models with domain experts. You can check out our docs here: (https://docs.finetunedb.com/) FinetuneDB exists because creating and managing high-quality datasets is a real bottleneck when fine-tuning LLMs. The quality of your data directly impacts the performance of your fine-tuned models, and existing tools didn’t offer an easy…
2024 · finetunedb.com
- 6
LLM reinforcement fine-tuning platform to improve LLM output
2025
- 7
- 8WM
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
2024 · glhf.chat
- 9IV
The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)
2024 · github.com
- 10
- 11FL
Hi HN community, I have been working on benchmarking publicly available LLMs these past couple of weeks. More precisely, I am interested on the finetuning piece since a lot of businesses are starting to entertain the idea of self-hosting LLMs trained on their proprietary data rather than relying on third party APIs. To this point, I am tracking the following 4 pillars of evaluation that businesses are typically look into: - Performance - Time to train an LLM - Cost to train an LLM - Inference (throughput / latency / cost per token) For each LLM, my aim is to benchmark them for…
2023 · github.com
- 12HI
I found that duplicating a specific block of 7 middle layers in Qwen2-72B, without modifying any weights, improved performance across all Open LLM Leaderboard benchmarks and took #1. As of 2026, the top 4 models on that leaderboard are still descendants. The weird finding: single-layer duplication does nothing. Too few layers, nothing. Too many, it gets worse. Only circuit-sized blocks of ~7 layers work. This suggests pretraining carves out discrete functional circuits in the layer stack that only work when preserved whole. The whole thing was developed on 2x RTX 4090s in my basement. I'm…
Mar 2026 · dnhkng.github.io
- 13TV
May 2026 · github.com
- 14L2
Hi all, today we're excited to launch LoraLand: 25 fine-tuned mistral-7b models that outperform #gpt4 on task-specific applications ranging from sentiment detection to question answering. All 25 fine-tuned models… - Outperform GPT-4, GPT-3.5-turbo, and mistral-7b-instruct for specific tasks - Are cost-effectively served from a single GPU through LoRAX - Were trained for less than $8 each on average You can prompt all of the fine-tuned models today and compare their results to mistral-7b-instruct in real time! We'd love to hear comments and feedback from the community
2024 · predibase.com
- 15SU
Here's a project I've been working on for the last few months. It's a new (I think) algorithm, that allows to adjust smoothly - and in real time - how many calculations you'd like to do during inference of an LLM model. It seems that it's possible to do just 20-25% of weight multiplications instead of all of them, and still get good inference results. I implemented it to run on M1/M2/M3 GPU. The mmul approximation itself can be pushed to run 2x fast before the quality of output collapses. The inference speed is just a bit faster than Llama.cpp's, because the rest of implementation…
2024 · asciinema.org
- 16
- 17
- 18
- 19L3
Hi everyone, I'm kinda involved in some retrogaming and with some experiments I ran into the following question: "It would be possible to run transformer models bypassing the cpu/ram, connecting the gpu to the nvme?" This is the result of that question itself and some weekend vibecoding (it has the linked library repository in the readme as well), it seems to work, even on consumer gpus, it should work better on professional ones tho
Feb 2026 · github.com
- 20
- 21
General Compute▲315AI models that run on an inference cloud optimized for speed
May 2026 · generalcompute.com
- 22ML
Aug 2026 · github.com
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →