Llama-Factory: Unified, Efficient Fine-Tuning for 100 Open Llms
Posted4 months agoActive4 months ago
github.comTechstory
supportivepositive
Debate
20/100
LLM Fine-TuningAI Model OptimizationNlp
Key topics
LLM Fine-Tuning
AI Model Optimization
Nlp
Llama-Factory is a unified and efficient platform for fine-tuning 100+ open LLMs, sparking discussion on its applications, GPU requirements, and comparisons to other similar libraries.
Snapshot generated from the HN discussion
Discussion Activity
Active discussionFirst comment
45m
Peak period
14
0-12h
Avg / period
4.8
Comment distribution19 data points
Loading chart...
Based on 19 loaded comments
Key moments
- 01Story posted
Sep 18, 2025 at 7:48 PM EDT
4 months ago
Step 01 - 02First comment
Sep 18, 2025 at 8:33 PM EDT
45m after posting
Step 02 - 03Peak activity
14 comments in 0-12h
Hottest window of the conversation
Step 03 - 04Latest activity
Sep 23, 2025 at 4:41 AM EDT
4 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45296403Type: storyLast synced: 11/20/2025, 12:53:43 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
I found this link more useful.
"LLaMA Factory is an easy-to-use and efficient platform for training and fine-tuning large language models. With LLaMA Factory, you can fine-tune hundreds of pre-trained models locally without writing any code."
Always curious to see what other ai enthusiasts are running!
on a related note, at what point are people going to get tired of waiting 20s for an llm to answer their questions? i wish it were more common for smaller models to be used when sufficient.
I've been trying to actually finetune Deepseek (not distills) and there are few options
Unsloth doesn't have an official multi-GPU story: there's hacked together solutions but they're finicky as it is for smaller models
In general Deepseek has very few resources on finetuning, that get even further muddied by people referring to the distills when they claim to be finetuning it.
On a side note, has anyone tried something similar? I have 100K messages and want to make a "dumb persona" which reflects the general Discord server vibe. I don't really care if it's accurate. What models would be most suitable for this task? My setup is not that powerful: 4070S, 32GB of RAM for training, Lenovo M715q for running with, Ryzen 5 PRO 2400GE, 16GB of memory.
https://www.nvidia.com/en-us/ai/nim-for-manufacturing/
Word on the street is the project has yielded largely unimpressive results compared to its potential, but NV is still investing in an attempt to further raise the GPU saturation waterline.
p.s. This project logo stood out to me at presenting the Llama releasing some "steam" with gusto. I wonder if that was intentional? Sorry for the immature take but stopping the scatological jokes is tough.