Tonic/multilingual-EMIR-reporting-csv
Viewer β’ Updated β’ 19.2k
Joseph [open/acc] Pollack PRO
Tonic
AI & ML interests
π€Making robots to help people learn things quicker π©π»βππ
Recent Activity
updated a dataset about 11 hours ago
Tonic/multilingual-EMIR-reporting-csv published a dataset about 11 hours ago
Tonic/multilingual-EMIR-reporting-csv updated a dataset about 11 hours ago
Tonic/multilingual-EMIR-reporting-jsonlOrganizations
updated a
dataset about 11 hours ago
published a
dataset about 11 hours ago
updated a
dataset about 11 hours ago
published a
dataset about 11 hours ago
updated a
dataset about 11 hours ago
published a
dataset about 11 hours ago
updated a
dataset 1 day ago
published a
dataset 1 day ago
updated a
dataset 1 day ago
published a
dataset 1 day ago
updated a
dataset 1 day ago
published a
dataset 1 day ago
updated a
dataset 1 day ago
published a
dataset 1 day ago
liked a
dataset 2 days ago
reacted to sergiopaniego's post with π 2 days ago
Post
2521
LFM2.5-2.6B just dropped!
and the @liquidai blog comes with some nice details about the training procedure, so let's analyze it.
basically, a full agent training pipeline but compressed into 2.6B
base model β SFT β specialized teachers per domain (SFT + RLVR) β on-policy distillation back into one student β agentic RL
the two most interesting stages
β MOPD: the student generates, each prompt routes to its domain teacher for token-level feedback. teachers branch from the same SFT checkpoint, so their signal stays close to the student's distribution
β agentic RL: multi-turn GRPO inside real harnesses (OpenClaw, Hermes Agent), one sandbox per rollout, a proxy captures token-level trajectories while the harness stays a black box
this makes a 2.6B that beats much larger models on instruction following and tool use
SFT, distillation, RL, RL envs: exactly what we're covering in our Training Agents livestream series (next one coming soon!)
β model: LiquidAI/LFM2.5-2.6B
β blog: https://www.liquid.ai/blog/lfm2-5-2-6b
β live series: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5
and the @liquidai blog comes with some nice details about the training procedure, so let's analyze it.
basically, a full agent training pipeline but compressed into 2.6B
base model β SFT β specialized teachers per domain (SFT + RLVR) β on-policy distillation back into one student β agentic RL
the two most interesting stages
β MOPD: the student generates, each prompt routes to its domain teacher for token-level feedback. teachers branch from the same SFT checkpoint, so their signal stays close to the student's distribution
β agentic RL: multi-turn GRPO inside real harnesses (OpenClaw, Hermes Agent), one sandbox per rollout, a proxy captures token-level trajectories while the harness stays a black box
this makes a 2.6B that beats much larger models on instruction following and tool use
SFT, distillation, RL, RL envs: exactly what we're covering in our Training Agents livestream series (next one coming soon!)
β model: LiquidAI/LFM2.5-2.6B
β blog: https://www.liquid.ai/blog/lfm2-5-2-6b
β live series: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5
- 3 replies
upvoted a changelog 17 days ago
Hugging Face Changelog
MCP Server Enhancements
β’ 195
liked a
model 17 days ago
reacted to nwaughachukwuma's post with β€οΈ 17 days ago
Post
735
# One API for Every Visual & OCR Models.
The VLM Run Gateway is a fully compatible API for OpenAI chat completions for visual intelligence. If youβre building document extraction or visual understanding, the Gateway exposes OCR, VQA, and detection behind a single interface you already know.
Read the docs: https://docs.vlm.run/gateway/introduction.
We actively support the following recent OCR and VQA models, which you can try today at no cost:
* zai-org/glm-ocr
* rednote-hilab/dots.mocr
* paddleocr/pp-ocrv6
* qwen/qwen3.5-0.8b
## Quickstart
### Python
### Curl
## Auth and limits
Anonymous auth is enabled, so you can omit the authorization header entirely, or send Bearer "" or Bearer vlmrun. Rate limits are 60 req/min and 1000 req/hr.
The VLM Run Gateway is a fully compatible API for OpenAI chat completions for visual intelligence. If youβre building document extraction or visual understanding, the Gateway exposes OCR, VQA, and detection behind a single interface you already know.
Read the docs: https://docs.vlm.run/gateway/introduction.
We actively support the following recent OCR and VQA models, which you can try today at no cost:
* zai-org/glm-ocr
* rednote-hilab/dots.mocr
* paddleocr/pp-ocrv6
* qwen/qwen3.5-0.8b
## Quickstart
### Python
from openai import OpenAI
client = OpenAI(base_url="https://gateway.vlm.run/v1/openai")
response = client.chat.completions.create(
model="zai-org/glm-ocr",
messages=[
{
"role": "user",
"content": [
{
"type": "document_url",
"document_url": {
"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
},
},
],
}
],
extra_body={"method": "markdown", "document_dpi": 150},
)
print(response.choices[0].message.content)### Curl
curl https://gateway.vlm.run/v1/openai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer vlmrun" \
-d '{
"model": "zai-org/glm-ocr",
"messages": [
{
"role": "user",
"content": [
{
"type": "document_url",
"document_url": {
"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/finance.sec-filings/tsla-8k.pdf"
}
}
]
}
],
"method": "markdown",
"document_dpi": 150
}'## Auth and limits
Anonymous auth is enabled, so you can omit the authorization header entirely, or send Bearer "" or Bearer vlmrun. Rate limits are 60 req/min and 1000 req/hr.
liked a
dataset 21 days ago