johnlockejrr/ppocrv6-sam-heb
Image-to-Text ā¢ Updated ā¢ 1
šļø Building on HF
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a model about 2 hours ago
johnlockejrr/ppocrv6-sam-heb updated a model about 2 hours ago
johnlockejrr/ppocrv6-sam-heb published a model about 2 hours ago
johnlockejrr/ppocrv6-sam-hebOrganizations
liked a
model about 2 hours ago
updated a
model about 2 hours ago
published a
model about 2 hours ago
upvoted a collection about 23 hours ago
liked a
model about 23 hours ago
reacted to badaoui's post with š 5 days ago
Post
2284
432 GB of ultra-fast HBM4 and up to 23.3 TB/s of memory bandwidth on a single GPU š¤Æ.
Two weeks ago, we got early access to AMD's new Instinct MI455X, and our first goal was simple: make sure š¤ Transformers works on day one.
Over the past few weeks, we worked closely with the AMD team to validate the platform, enable Flash Attention, add torchcodec support for multimodal models, and resolve issues uncovered during testing.
The result:
ā 99.5% success rate across our 24 core Transformers model architectures - already on par with our daily CI on previous AMD and NVIDIA platforms.
The hardware is just as exciting. With 432 GB of HBM per GPU, our early capacity experiments showed more than 3Ć the concurrent long-context requests compared to MI300, thanks to the much larger KV cache capacity.
A huge thanks to the AMD team for the early access and the great collaboration!
Read the full blog š
https://huggingface.co/blog/badaoui/transformers-on-amd-mi455
Two weeks ago, we got early access to AMD's new Instinct MI455X, and our first goal was simple: make sure š¤ Transformers works on day one.
Over the past few weeks, we worked closely with the AMD team to validate the platform, enable Flash Attention, add torchcodec support for multimodal models, and resolve issues uncovered during testing.
The result:
ā 99.5% success rate across our 24 core Transformers model architectures - already on par with our daily CI on previous AMD and NVIDIA platforms.
The hardware is just as exciting. With 432 GB of HBM per GPU, our early capacity experiments showed more than 3Ć the concurrent long-context requests compared to MI300, thanks to the much larger KV cache capacity.
A huge thanks to the AMD team for the early access and the great collaboration!
Read the full blog š
https://huggingface.co/blog/badaoui/transformers-on-amd-mi455
- 1 reply
liked a
model 5 days ago
deepreinforce-ai/Ornith-1.0-9B is better than empero-ai/Qwythos-9B-Claude-Mythos-5-1M
š„ 4
2
#10 opened 28 days ago
by 
tooltd
When will Ornit-2.0 will release based on Qwen-3.6-35b-a3b
š 3
2
#27 opened 18 days ago
by 
rbtasd
liked a
model 20 days ago
reacted to MiniMax-AI's post with š 21 days ago
Post
4682
Huge news from MiniMax: weāve secured a $2B funding round, paired with a formal long-term commitment from our CEO IO to allocate 1% of total company equity from his personal holdings to support the global open-source AI community over the next four years.
This capital backs our continuous open model releases, community tooling and transparent frontier AI research. Weāre just getting started on our open-source roadmap toward accessible AGI.
If you build with open foundation models and want to push frontier AI together, come join us.
Intelligence with Everyone. š
MiniMaxAI
This capital backs our continuous open model releases, community tooling and transparent frontier AI research. Weāre just getting started on our open-source roadmap toward accessible AGI.
If you build with open foundation models and want to push frontier AI together, come join us.
Intelligence with Everyone. š
- 3 replies
liked a
model about 1 month ago
Cannot edit ? Served with ollama
2
#32 opened about 1 month ago
by 
Toutatis64
liked 2
models about 1 month ago
reacted to pankajpandey-dev's post with š about 1 month ago
Post
7838
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 about 1 month ago
by 
agomberto
HF space doesn't load
2
#1 opened about 1 month ago
by johnlockejrr
updated 2
datasets about 1 month ago