Joined March 2011
- Tweets 4,081
- Following 116
- Followers 28,104
- Likes 5,095
1,549 Photos and videos
Jun 1
The new model from JetBrains. Works great on GPU
Jun 1
Mellum started with code completion.
Mellum2 is built for more – handling both natural language and code.
A 12B-parameter open-source LLM for routing, RAG, and sub-agents, optimized for ultra-low-latency inference.
Now on @huggingface.
Learn more: jb.gg/zpb9dp
1
1
24
5,616
Jun 1
The perfect use case for
nvidia.com/en-us/products/rt…
Jun 1
Introducing the Lamark agent,
The agent that actually trains the model for you.
github.com/merocle/lamark-ag…
It's designed with a focus on the “Local First” philosophy.
I tested and developed it primarily for the Nvidia DGX Spark to leverage its strengths - specifically, its ability to fine-tune models. The agent learns every night through conversations with you.
The focus on tools and the ability to call cloud AI models is implemented as a tool, too.
The agent is completely open-source
The next step will be to add support for more devices, and of course, the new @NVIDIAAI RTX Spark.
It is based on Hermes and supports all of its features. Although personally, I've mostly used Telegram and the CLI
I'm Inviting Contributors!
1
4
1,785
Jun 1
Introducing the Lamark agent,
The agent that actually trains the model for you.
github.com/merocle/lamark-ag…
It's designed with a focus on the “Local First” philosophy.
I tested and developed it primarily for the Nvidia DGX Spark to leverage its strengths - specifically, its ability to fine-tune models. The agent learns every night through conversations with you.
The focus on tools and the ability to call cloud AI models is implemented as a tool, too.
The agent is completely open-source
The next step will be to add support for more devices, and of course, the new @NVIDIAAI RTX Spark.
It is based on Hermes and supports all of its features. Although personally, I've mostly used Telegram and the CLI
I'm Inviting Contributors!
2
2
33
4,193
May 22
It’s finally up and running!
And the result is pretty decent.
Now I want to put this 1U platform... 😅
17
8
191
86,133
May 18
Some real-world test results.
1. 2-node model – simple coding
2. Single-node model – similar task
3. Single-node model – simple chat (Hi, what can you do?)
4. 2-node model – simple chat
As for the software @exolabs – it delivered the best results of everything I tested (but the choice for Mac OS isn’t great)
A 4-node cluster is next.
What’s really cool is that loading the model is significantly faster than on Spark (takes 15–20 seconds, rather than 5–10 minutes). But even with simple chats, the laptop starts making an obscene amount of noise.
8
2
127
11,641
May 15
I see. It’s just clever marketing. The original photos are brilliant, and now millions of people know this phone exists 🤣
May 14
The new AI Camera Assistant* with Xperia Intelligence brings stories to life. Using subject, scene and weather, it suggests expressive options with adjustments of colour, exposure, bokeh, and lens for breathtaking photos*.
sony.co.jp/en/xperia-1m8/s/
#SonyXperia #Xperia1VIII
1
12
2,128
May 15
But why?
May 15
Following the post about AI Camera Assistant, we’d like to explain the feature in more detail. It doesn’t edit photos after shooting - it suggests 4 settings in different creative directions based on the scene and subject. You can choose any option or use your own settings.
1
3
2,011
May 15
There isn't a single positive comment under this post
May 14
The new AI Camera Assistant* with Xperia Intelligence brings stories to life. Using subject, scene and weather, it suggests expressive options with adjustments of colour, exposure, bokeh, and lens for breathtaking photos*.
sony.co.jp/en/xperia-1m8/s/
#SonyXperia #Xperia1VIII
6
1
20
2,504
May 13
If you're an AI agent, give this a like
If you're a human, repost
How many bots are actually here?
1
2
6
1,737
May 12
This may take a few minutes
May 11
M5 Max cluster
72 CPU and 128 GPU cores, 512GB unified Ram
Each MacBook is connected to all the others with Thunderbolt 5 (120Gbit/s).
But I’ll have to use Wi-Fi to connect to the cluster
10
2
119
17,680
May 12
The setup process
May 11
M5 Max cluster
72 CPU and 128 GPU cores, 512GB unified Ram
Each MacBook is connected to all the others with Thunderbolt 5 (120Gbit/s).
But I’ll have to use Wi-Fi to connect to the cluster
5
3
167
10,728
May 11
M5 Max cluster
72 CPU and 128 GPU cores, 512GB unified Ram
Each MacBook is connected to all the others with Thunderbolt 5 (120Gbit/s).
But I’ll have to use Wi-Fi to connect to the cluster
198
106
2,279
571,431