Holo4: powering generalist computer-use agents
• 85
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
Surfer 2: The Next Generation of Cross-Platform Computer Use Agents
Articles
sergiopaniego
posted an update 36 minutes ago
Post
7
sharing the slides from my talk at Kernel Panic in Madrid
It's basically "The ultimate guide to multi-harness RL" turned slides and condensed into a 20 min talk
FineEnvs/multi-harness-rl-slides
congrats to @Helmcode for the organization!
blog: FineEnvs/multi-harness-rl
It's basically "The ultimate guide to multi-harness RL" turned slides and condensed into a 20 min talk
FineEnvs/multi-harness-rl-slides
congrats to @Helmcode for the organization!
blog: FineEnvs/multi-harness-rl
sergiopaniego
posted an update about 20 hours ago
Post
102
Repo2RLEnv just shipped TaskSmith + 50 high quality RL envs generated from HF repos 🔨
TaskSmith is a specialized harness that turns a merged PR into a verified RL env
the envs come from HF repos (Transformers, TRL, PEFT, Accelerate, Diffusers), shipped as Harbor tasks you can eval or train on
> code: github.com/huggingface/Repo2RLEnv
> dataset: huggingface.co/datasets/FineEnvs/HF_ML_Tasksmith
TaskSmith is a specialized harness that turns a merged PR into a verified RL env
the envs come from HF repos (Transformers, TRL, PEFT, Accelerate, Diffusers), shipped as Harbor tasks you can eval or train on
> code: github.com/huggingface/Repo2RLEnv
> dataset: huggingface.co/datasets/FineEnvs/HF_ML_Tasksmith
sergiopaniego
posted an update 2 days ago
Post
3272
ThinkingBox from @microsoft is now available as an OpenEnv env (cc @tuhink 🤗 )!
> ThinkingBox is a sandbox for testing agents on business workflows. it simulates a customer, gives the agent MCP tools over a real database, and at the end checks what changed in that database instead of trusting the agent's last message
> ThinkingBox-Bench is the benchmark built on it: 507 tasks across retail, insurance, travel, banking and consulting
> the OpenEnv env runs each task as an episode in its own isolated backend and returns a pass/fail reward from those checks
https://huggingface.co/blog/microsoft/thinkingbox
> ThinkingBox is a sandbox for testing agents on business workflows. it simulates a customer, gives the agent MCP tools over a real database, and at the end checks what changed in that database instead of trusting the agent's last message
> ThinkingBox-Bench is the benchmark built on it: 507 tasks across retail, insurance, travel, banking and consulting
> the OpenEnv env runs each task as an episode in its own isolated backend and returns a pass/fail reward from those checks
https://huggingface.co/blog/microsoft/thinkingbox
sergiopaniego
posted an update 5 days ago
Recommended sampling parameters for Holo4-35B-A3B GGUF?
1
#3 opened 8 days ago
by 
itzRomeo
mbrunel-H
updated a
dataset 8 days ago
经典鹈鹕骑自行车测试
3
#2 opened 9 days ago
by itzRomeo
Add license files and update model card
#1 opened 9 days ago
by 
h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Add license files and update model card
#1 opened 9 days ago
by h-tonywu
Article
Holo4: powering generalist computer-use agents
Hcompany
• • 85 h-tonywu
published 2
models 9 days ago