Sam Joshua

SamJoshua's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in swiss-ai/Apertus-8B-Instruct-2509 about 4 hours ago

Sync chat_template.jinja with vLLM's Apertus tool template so tools render in transformers

#36 opened about 4 hours ago by

SamJoshua

New activity in ibm-granite/granite-4.1-3b about 15 hours ago

chat_template: tool_call.name is concatenated into JSON without escaping — name rewrite / key injection on re-render

#7 opened about 15 hours ago by

SamJoshua

New activity in nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1 about 15 hours ago

expected_action calls tools not in `tools` (45 rows); 8 more have capitalized arg keys; README row count is wrong

#1 opened about 15 hours ago by

SamJoshua

New activity in Qwen/Qwen3.8-27B about 15 hours ago

chat_template: OpenAI-style string tool_call.arguments still crashes with TypeError on |items

👍 1

#240 opened about 15 hours ago by

SamJoshua

New activity in openbmb/MiniCPM5-2B about 16 hours ago

chat_template: string tool-call arguments crash rendering, and non-string values are written as Python repr instead of JSON

#30 opened about 16 hours ago by

SamJoshua

New activity in microsoft/OmniParser-v2.0 about 17 hours ago

`handler.py` checks for `"RBGA"` (typo) so RGBA screenshots never convert — plus Hub `intersection_area` still wrong

#38 opened about 17 hours ago by

SamJoshua

New activity in patronus-studio/wolf-defender-prompt-injection about 17 hours ago

Mixed / int8_int4 ONNX exports are non-deterministic on CPU (same input → INJECTION or BENIGN)

6

#3 opened about 21 hours ago by

SamJoshua

New activity in nvidia/Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1 about 19 hours ago

Tool schemas use two different formats, and 3 records have target_args that can never trigger the verifier

#1 opened about 19 hours ago by

SamJoshua

New activity in protectai/deberta-v3-base-prompt-injection-v2 about 22 hours ago

Quick start truncates at 512 tokens: injections after that are never scored (tested, with a chunked fix)

#11 opened about 22 hours ago by

SamJoshua

New activity in Qwen/Qwen2.5-Coder-1.5B-Instruct about 23 hours ago

Tested smolagents CodeAgent example for this model

#10 opened about 23 hours ago by

SamJoshua

New activity in smolagents/aguvis-stage-2 about 23 hours ago

Add dataset card: description, format, configs, and quick start

#3 opened about 23 hours ago by

SamJoshua

New activity in smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI about 23 hours ago

Fix model card: base model, title, and image-text-to-text quick start

#3 opened about 23 hours ago by

SamJoshua

New activity in huggingface/InferenceSupport 5 months ago

OBLITERATUS/Gemma-4-12B-OBLITERATED

👍 3

#10386 opened 5 months ago by

SamJoshua