empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF
Image-Text-to-Text ā¢ 9B ā¢ Updated ā¢ 1.46M ā¢ 1.41k
šļø Building on HF
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a model 3 days ago
empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF new activity 3 days ago
deepreinforce-ai/Ornith-1.0-35B-GGUF:Cannot edit ? Served with ollama liked a model 4 days ago
deepreinforce-ai/Ornith-1.0-35B-GGUFOrganizations
liked a
model 3 days ago
Cannot edit ? Served with ollama
2
#32 opened 3 days ago
by 
Toutatis64
liked 2
models 4 days ago
reacted to pankajpandey-dev's post with š 6 days ago
Post
7804
š®š³ New in my Hindi LLM Series: Gemma-4 E4B, fine-tuned for Hindi ā 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 š
ā My fine-tune is more concise ā ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
ā Pure native Hindi ā base keeps slipping into English ("ą¤øą¤ą¤¤ą„ą¤²ą¤æą¤¤ ą¤ą¤¹ą¤¾ą¤° (Eat a Balanced Diet)", "ą¤¤ą¤¾ą¤°ą¤¾ (Star)"). My fine-tune stays in clean Hindi.
ā Tighter instruction-following ā ask for a "short message" and it gives one, not a menu of options.
āļø And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model ā I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
š 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 Ā· Data by @ai4bharat š
#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 š
ā My fine-tune is more concise ā ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
ā Pure native Hindi ā base keeps slipping into English ("ą¤øą¤ą¤¤ą„ą¤²ą¤æą¤¤ ą¤ą¤¹ą¤¾ą¤° (Eat a Balanced Diet)", "ą¤¤ą¤¾ą¤°ą¤¾ (Star)"). My fine-tune stays in clean Hindi.
ā Tighter instruction-following ā ask for a "short message" and it gives one, not a menu of options.
āļø And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model ā I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
š 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 Ā· Data by @ai4bharat š
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
- 12 replies
How to get the data?
4
#2 opened 12 days ago
by 
agomberto
HF space doesn't load
2
#1 opened 10 days ago
by johnlockejrr
updated 2
datasets 9 days ago
Hallucination
3
#6 opened 10 days ago
by johnlockejrr
updated a
dataset 12 days ago
published a
dataset 12 days ago
liked a
model 13 days ago
Some people steal from you
1
#1 opened 15 days ago
by johnlockejrr
Language
2
#3 opened 16 days ago
by johnlockejrr
liked a
dataset 15 days ago
liked a
model 15 days ago
liked a
model 16 days ago
