pcuenq/Qwen3.5-397B-A17B-4bit
Text Generation • 396B • Updated
• 1.66k
Pedro Cuenca PRO
pcuenq
AI & ML interests
None yet
Recent Activity
upvoted an article about 9 hours ago
Bringing Autonomous Driving RL to OpenEnv and TRL reacted
to
sergiopaniego's
post with 🚀 about 9 hours ago
What happens when you make an LLM drive a car where physics are real and actions can't be undone?
I ported CARLA, the autonomous driving simulator, to OpenEnv and added training support via TRL + Hugging Face Spaces.
The model interacts with the simulator through tool calls (observe, brake, change lane) and learns from a reward signal.
In 50 training steps, Qwen 0.6B learns to swerve and brake to avoid pedestrians in emergency situations.
The project supports text and vision (VLMs can see through a camera sensor), open-world driving with traffic, and multiple driving scenarios.
This builds on the carla-env project by sinatras, which originally placed LLMs inside CARLA for evaluation. We extended it with vision, new scenarios, rubric-based rewards, and made it trainable end-to-end.
Blog: https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl/
CARLA env in OpenEnv: https://github.com/meta-pytorch/OpenEnv/tree/main/envs/carla_env
Training script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla.py upvoted an article about 14 hours ago
Mixture of Experts (MoEs) in Transformers Organizations
pcuenq/sam2-hiera-large
Mask Generation • 0.2B • Updated
• 2
pcuenq/candle-depth-anything-v2-small
Updated
pcuenq/nvidia-nano-clone
Image-Text-to-Text • 13B • Updated
• 2
pcuenq/paddle-test-7
Image-Text-to-Text • Updated
• 4
pcuenq/paddle-test-6
Image-Text-to-Text • 1.0B • Updated
• 2
pcuenq/paddle-test-5
Image-Text-to-Text • 1.0B • Updated
• 8
pcuenq/paddle-test-4
Image-Text-to-Text • 1.0B • Updated
• 4
pcuenq/paddle-test-3
Image-Text-to-Text • 1.0B • Updated
• 1
pcuenq/paddle-test-2
Image-Text-to-Text • 1.0B • Updated
• 3
pcuenq/paddle-test-1
Image-Text-to-Text • Updated
• 2
pcuenq/PaddleOCR-VL-0.9B
Image-Text-to-Text • 1.0B • Updated
• 186 • 1
pcuenq/stable-diffusion-v1-5
Text-to-Image • Updated
• 28
pcuenq/sdxl-turbo
Text-to-Image • Updated
• 10
pcuenq/canary-sp-model
Updated
pcuenq/Qwen3-235B-A22B-Instruct-2507-mlx-4Bit
Text Generation • 235B • Updated
• 19 • 1
pcuenq/Phi-4-mini-instruct-mlx-4Bit
Text Generation • 0.6B • Updated
• 33 • 1
pcuenq/Phi-4-mini-instruct-mlx-8Bit
Text Generation • 1B • Updated
• 24
pcuenq/Baichuan-M1-14B-Instruct-tokenizer
Text Generation • Updated
• 1
pcuenq/Hunyuan-7B-Instruct-tokenizer
Text Generation • Updated
• 1
pcuenq/marigold-coco-segmentation
Updated
• 1
pcuenq/t
Updated
pcuenq/gated-test
Text Generation • Updated
pcuenq/DeepSeek-R1-Distill-Qwen-32B-Q2-6
Text Generation • 4B • Updated
• 11 • 1
pcuenq/jh_dreambooth_1000
Text-to-Image • Updated
• 32 • 1
pcuenq/gemma-2-2b-it-Q4_K_M
Text Generation • 0.4B • Updated
• 10
pcuenq/gpt2-finetuned-cnn-summarization-v2-tokenizer
Text Generation • Updated
pcuenq/smol-lfs
Updated
pcuenq/vit_large_patch14_dinov2.lvd142m
Image Feature Extraction • Updated
• 3
pcuenq/vit_base_patch32_clip_448.laion2b_ft_in12k_in1k
Image Classification • Updated
• 2