moonshotai/Kimi-K3
Image-Text-to-Text • 2.8T • Updated • 99.2k • • 8.15k
Michael Salaverry
barakplasma
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
moonshotai/Kimi-K3 liked a model 8 days ago
XiaomiRobotics/Xiaomi-Robotics-U0 liked a model 8 days ago
XiaomiRobotics/Xiaomi-Robotics-0-LIBEROOrganizations
liked a
model 1 day ago
liked 2
models 8 days ago
liked a
Space 12 days ago
liked 2
models 13 days ago
liked a
Space 14 days ago
liked a
model 14 days ago
liked 2
models 15 days ago
liked a
Space 19 days ago
liked a
model 21 days ago
liked a
model 25 days ago
upvoted a collection 25 days ago
liked a
Space 26 days ago
updated a
model 28 days ago
reacted to pankajpandey-dev's post with 🔥 about 1 month ago
Post
7836
🇮🇳 New in my Hindi LLM Series: Gemma-4 E4B, fine-tuned for Hindi — and it runs on your laptop's CPU.
I fine-tuned Google's new Gemma-4 E4B on ~10k Hindi instruction pairs (AI4Bharat: anudesh + dolly) using Unsloth + LoRA, on a single L4 GPU.
Then I ran an honest side-by-side eval: base Gemma-4 vs my fine-tune, across 25 Hindi prompts. The results were interesting 👇
✅ My fine-tune is more concise — ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
✅ Pure native Hindi — base keeps slipping into English ("संतुलित आहार (Eat a Balanced Diet)", "तारा (Star)"). My fine-tune stays in clean Hindi.
✅ Tighter instruction-following — ask for a "short message" and it gives one, not a menu of options.
⚖️ And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model — I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
🔗 Try it:
Live demo (CPU): pankajpandey-dev/gemma-4-e4b-hindi-demo
GGUF (Ollama/llama.cpp): pankajpandey-dev/gemma-4-e4b-hindi-instruct-GGUF
16-bit model: pankajpandey-dev/gemma-4-e4b-hindi-instruct
Built with @unsloth · Data by @ai4bharat 🙏
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
I fine-tuned Google's new Gemma-4 E4B on ~10k Hindi instruction pairs (AI4Bharat: anudesh + dolly) using Unsloth + LoRA, on a single L4 GPU.
Then I ran an honest side-by-side eval: base Gemma-4 vs my fine-tune, across 25 Hindi prompts. The results were interesting 👇
✅ My fine-tune is more concise — ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
✅ Pure native Hindi — base keeps slipping into English ("संतुलित आहार (Eat a Balanced Diet)", "तारा (Star)"). My fine-tune stays in clean Hindi.
✅ Tighter instruction-following — ask for a "short message" and it gives one, not a menu of options.
⚖️ And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model — I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
🔗 Try it:
Live demo (CPU): pankajpandey-dev/gemma-4-e4b-hindi-demo
GGUF (Ollama/llama.cpp): pankajpandey-dev/gemma-4-e4b-hindi-instruct-GGUF
16-bit model: pankajpandey-dev/gemma-4-e4b-hindi-instruct
Built with @unsloth · Data by @ai4bharat 🙏
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
- 12 replies
liked 3
models about 1 month ago
