The request "tiny-GptOssForCausalLM" names a Hugging Face Transformers model class (a tiny GPT-OSS causal language model), and none of the candidates' sources describes that class directly. The closest matches are Hugging Face's ecosystem for models and small agent tooling 6, and fast.ai for training and fine-tuning neural nets 2. Note that the request names a model class rather than a software product, so a clarification about the intended task could narrow this.
A question back: Do you want to load and run an existing tiny GPT-OSS checkpoint, or train or fine-tune one from scratch?
- 1
Hugging Face Tiny Agentshuggingface.coverified and signed
Hugging Face's hub hosts and serves machine learning models, and Tiny Agents is its lightweight agent SDK, which could be used to load and run a small model from the hub 6.
official:SDK · @huggingface/tiny-agents
for agents: llm · tiny-agent · huggingface
- 2
fast.aifast.aiverified and signed
fast.ai offers courses and a fastai library for PyTorch that teach and build neural network models, which could be used to train or experiment with a tiny causal language model 2.
+462 community tools built for it
for agents: github · python · api
Sources
- 2fast.ai—Making neural nets uncool again – fast.aifast.ai · read 2026-10-29
- 6Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
For agents: the 10 actions behind this answer
create-llms · create-llms verified and signed
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
github · ghapi verified and signed
shell · shin-watcher-oss found in code, not yet checked
Run a shell command in the cloned BerriAI/litellm working tree. Use this for git, uv, curl, ls, cat, pytest, etc.
openai/gpt-4o-mini · openai/gpt-4o-mini verified and signed
Low latency, low cost version of OpenAI's GPT-4o model
· SGLang website read, tools not yet checked
SGLang powers fast, scalable inference for large language and multimodal models. Open-source serving framework with state-of-the-art performance.
nateraw/goliath-120b · nateraw/goliath-120b verified and signed
An auto-regressive causal LM created by combining 2x finetuned Llama-2 70B into one.
llm · @huggingface/tiny-agents verified and signed
openai/gpt-5-nano · openai/gpt-5-nano verified and signed
Fastest, most cost-effective GPT-5 model from OpenAI
prunaai/gpt-oss-120b-fast · prunaai/gpt-oss-120b-fast verified and signed
This is a version of GPT-OSS-120B that is optimised by Pruna AI.
openai/gpt-4.1-mini · openai/gpt-4.1-mini verified and signed
Fast, affordable version of GPT-4.1
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.