johnlockejrr/LightOnOCR-2-1B-base-samaritan
Image-Text-to-Text
•
1B
•
Updated
•
5
John Locke
johnlockejrr
·
AI & ML interests
NLP, OCR, AI
Recent Activity
new activity
about 4 hours ago
lightonai/LightOnOCR-2-1B-base:Training Unicode Normalization
updated
a model
2 days ago
johnlockejrr/LightOnOCR-2-1B-base-samaritan
new activity
3 days ago
wjbmattingly/LightOnOCR-2-1B-old-church-slavonic-mixed:`max_new_tokens=256`
Organizations
Training Unicode Normalization
#1 opened about 4 hours ago
by
johnlockejrr
updated
a
model
2 days ago
`max_new_tokens=256`
#1 opened 3 days ago
by
johnlockejrr
reacted to
danielhanchen's
post with 🚀
4 days ago
Post
3251
You can now run Kimi K2.5 locally! 🔥
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
- 7 replies
reacted to
scthornton's
post with 👍
5 days ago
Post
2116
SecureCode: security-aware code models (3B–20B), trained for review + remediation
I’ve been frustrated by how often code assistants recommend patterns that pass tests but fail security review (e.g., string-built SQL, brittle auth logic, unsafe parsing, insecure defaults, etc.). So I built **SecureCode**: a collection of **8 code models (3B → 20B)** trained to behave more like a security reviewer.
What you should expect from SecureCode:
- identify likely vuln patterns and explain *why* they’re risky
- outline plausible abuse paths (defensive framing)
- propose a secure rewrite (drop-in where possible)
- include defense-in-depth guidance + regression tests/checks
Links:
- **Models:** https://huggingface.co/collections/scthornton/securecode
- **Dataset:** scthornton/securecode-v2
- **Paper:** https://arxiv.org/html/2512.18542v1 SecureCode v2.0: A Production-Grade Dataset for Training Security-Aware Code Generation Models (2512.18542)
**How to test it (copy/paste prompt):**
**I’m looking for real-world feedback**
- Your “this slipped through review once” snippets (sanitized is fine)
- False positives / false negatives you observe
- Contributions of new CVE-grounded examples
If you drop a snippet, please include language/framework + what the *correct* remediation looks like in your environment. If you have any contributions or suggestions for the dataset, I'd be happy to hear them. I have some new features and enhancements planned for v3 that are already underway, but for now, I'm focused on testing as many use cases as possible. Appreciate you all!
I’ve been frustrated by how often code assistants recommend patterns that pass tests but fail security review (e.g., string-built SQL, brittle auth logic, unsafe parsing, insecure defaults, etc.). So I built **SecureCode**: a collection of **8 code models (3B → 20B)** trained to behave more like a security reviewer.
What you should expect from SecureCode:
- identify likely vuln patterns and explain *why* they’re risky
- outline plausible abuse paths (defensive framing)
- propose a secure rewrite (drop-in where possible)
- include defense-in-depth guidance + regression tests/checks
Links:
- **Models:** https://huggingface.co/collections/scthornton/securecode
- **Dataset:** scthornton/securecode-v2
- **Paper:** https://arxiv.org/html/2512.18542v1 SecureCode v2.0: A Production-Grade Dataset for Training Security-Aware Code Generation Models (2512.18542)
**How to test it (copy/paste prompt):**
> You are a senior application security engineer. Review the code below.
> Output: (1) findings with severity, (2) likely exploit scenarios (high level), (3) secure rewrite,
> (4) defense-in-depth recommendations, (5) regression tests/checks.
> Code: `...`**I’m looking for real-world feedback**
- Your “this slipped through review once” snippets (sanitized is fine)
- False positives / false negatives you observe
- Contributions of new CVE-grounded examples
If you drop a snippet, please include language/framework + what the *correct* remediation looks like in your environment. If you have any contributions or suggestions for the dataset, I'd be happy to hear them. I have some new features and enhancements planned for v3 that are already underway, but for now, I'm focused on testing as many use cases as possible. Appreciate you all!
upvoted
a
collection
5 days ago
liked
a
model
5 days ago
Experience on finetuning for specific language
2
#13 opened 9 days ago
by
Huy227
vLLM or Llama.cpp output
7
#1 opened 8 days ago
by
johnlockejrr
published
a
model
9 days ago
updated
a
dataset
9 days ago
liked
a
model
9 days ago
LightOnOCR-2-1B with Samaritan Hebrew
❤️
3
#10 opened 10 days ago
by
johnlockejrr
published
a
dataset
10 days ago
upvoted
a
paper
10 days ago
Finetune `nvidia/nemotron-ocr-v1` recognition model
5
#7 opened about 1 month ago
by
johnlockejrr
upvoted
an
article
12 days ago
Article
LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR
•
73
liked
a
model
12 days ago
liked
a
dataset
12 days ago
reacted to
diwank's
post with 🔥
15 days ago
Post
1516
Excited to announce *Open Responses* – a self-hosted alternative to OpenAI's new _Responses API_ that you can run locally, and use with ANY LLM model / provider and not just with OpenAI Responses API. What's more is that this is also compatible with their agents-sdk so everything just works out of the box!
To try it out, just run
Would love feedback and support for adding local HF models, @akhaliq @bartowski @prithivMLmods @julien-c @clefourrier @philschmid
We’d love feedback from the Hugging Face community on how it integrates with your pipelines (support for Hugging Face models landing soon!). Let’s push open-source AI forward together!
Docs:
https://docs.julep.ai/responses/quickstart
Repo:
https://github.com/julep-ai/open-responses
agents-sdk:
https://platform.openai.com/docs/guides/agents
To try it out, just run
npx -y open-responses init (or uvx) and that's it! :)Would love feedback and support for adding local HF models, @akhaliq @bartowski @prithivMLmods @julien-c @clefourrier @philschmid
We’d love feedback from the Hugging Face community on how it integrates with your pipelines (support for Hugging Face models landing soon!). Let’s push open-source AI forward together!
Docs:
https://docs.julep.ai/responses/quickstart
Repo:
https://github.com/julep-ai/open-responses
agents-sdk:
https://platform.openai.com/docs/guides/agents
- 3 replies