{"schema_version":"onlylabs.public_signal.v1","title":"Cerebras Repo: Cerebras/gigaGPT","description":"Cerebras repo signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478","json_url":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478/signal.json","generated_at":"2026-06-11T04:10:12.799786+00:00","org":{"slug":"cerebras","name":"Cerebras","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/cerebras","dossier_json_url":"https://onlylabs.fyi/labs/cerebras/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478","signal_json":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478/signal.json","source":"https://github.com/Cerebras/gigaGPT","lab_dossier":"https://onlylabs.fyi/labs/cerebras","lab_dossier_json":"https://onlylabs.fyi/labs/cerebras/dossier.json","analysis":"https://onlylabs.fyi/analysis/cerebras","analysis_json":"https://onlylabs.fyi/analysis/cerebras/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/cerebras/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":null},"answer_pack":{"answer":"Cerebras published Cerebras/gigaGPT (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo Cerebras/gigaGPT · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","signal_desk":"repos","source_context":{"source_url":"https://github.com/Cerebras/gigaGPT","source_host":"github.com","occurred_at":"2023-12-04T18:39:51+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"Cerebras","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"Cerebras/gigaGPT","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"333","source":"traction"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"label":"Watch term","value":"Infrastructure","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/Cerebras/gigaGPT"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T04:10:12.799786+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478/signal.json","dossier_json":"https://onlylabs.fyi/labs/cerebras/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/cerebras/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/cerebras/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","evidence_focus":["repo name","owner","description","language","stars","source URL","first seen time","data, eval, infra, safety, and product terms"],"extraction_questions":["What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Is the repo new evidence for a lab direction that is not yet in writing or releases?","Which related signals should an analyst inspect next?"],"signal_questions":["What does this new repository reveal before a formal announcement exists?","What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, interpret the repository as source-grounded category strategy evidence.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478/signal.json","required":true},{"label":"source","url":"https://github.com/Cerebras/gigaGPT","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/cerebras/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/cerebras/evidence.json","required":true},{"label":"topic_signals_json","url":null,"required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Cerebras's repo signal \"Cerebras/gigaGPT\" for neocloud strategy."},"semantic_triples":[{"subject":"Cerebras","predicate":"published repo","object":"Cerebras/gigaGPT","text":"Cerebras published repo Cerebras/gigaGPT."},{"subject":"Cerebras/gigaGPT","predicate":"is classified as","object":"repo signal","text":"Cerebras/gigaGPT is classified as repo signal."},{"subject":"Cerebras/gigaGPT","predicate":"belongs to","object":"repos desk","text":"Cerebras/gigaGPT belongs to repos desk."},{"subject":"Cerebras/gigaGPT","predicate":"has context","object":"Python","text":"Cerebras/gigaGPT has context Python."},{"subject":"Cerebras/gigaGPT","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Cerebras/gigaGPT has evidence coverage 1 captured evidence page."},{"subject":"Cerebras/gigaGPT","predicate":"has captured page count","object":"1","text":"Cerebras/gigaGPT has captured page count 1."},{"subject":"Cerebras/gigaGPT","predicate":"has readable page count","object":"1","text":"Cerebras/gigaGPT has readable page count 1."},{"subject":"Cerebras/gigaGPT","predicate":"has related signal count","object":"6","text":"Cerebras/gigaGPT has related signal count 6."},{"subject":"Cerebras/gigaGPT","predicate":"has analysis playbook objective","object":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","text":"Cerebras/gigaGPT has analysis playbook objective Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.."},{"subject":"Cerebras/gigaGPT","predicate":"has source host","object":"github.com","text":"Cerebras/gigaGPT has source host github.com."},{"subject":"Cerebras/gigaGPT","predicate":"has lab","object":"Cerebras","text":"Cerebras/gigaGPT has lab Cerebras."},{"subject":"Cerebras/gigaGPT","predicate":"has signal desk","object":"repos","text":"Cerebras/gigaGPT has signal desk repos."},{"subject":"Cerebras/gigaGPT","predicate":"has source host","object":"github.com","text":"Cerebras/gigaGPT has source host github.com."},{"subject":"Cerebras/gigaGPT","predicate":"has repository","object":"Cerebras/gigaGPT","text":"Cerebras/gigaGPT has repository Cerebras/gigaGPT."},{"subject":"Cerebras/gigaGPT","predicate":"has language","object":"Python","text":"Cerebras/gigaGPT has language Python."},{"subject":"Cerebras/gigaGPT","predicate":"has stars","object":"333","text":"Cerebras/gigaGPT has stars 333."},{"subject":"Cerebras/gigaGPT","predicate":"has watch term","object":"Eval methodology","text":"Cerebras/gigaGPT has watch term Eval methodology."},{"subject":"Cerebras/gigaGPT","predicate":"has watch term","object":"Data pipeline","text":"Cerebras/gigaGPT has watch term Data pipeline."}]},"intelligence":{"signal_desk":"repos","answer":"Cerebras published Cerebras/gigaGPT (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo Cerebras/gigaGPT · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","semantic_triples":[{"subject":"Cerebras","predicate":"published repo","object":"Cerebras/gigaGPT","text":"Cerebras published repo Cerebras/gigaGPT."},{"subject":"Cerebras/gigaGPT","predicate":"is classified as","object":"repo signal","text":"Cerebras/gigaGPT is classified as repo signal."},{"subject":"Cerebras/gigaGPT","predicate":"belongs to","object":"repos desk","text":"Cerebras/gigaGPT belongs to repos desk."},{"subject":"Cerebras/gigaGPT","predicate":"has context","object":"Python","text":"Cerebras/gigaGPT has context Python."},{"subject":"Cerebras/gigaGPT","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Cerebras/gigaGPT has evidence coverage 1 captured evidence page."}]},"signal":{"id":"6d7906b0-6cbd-4378-8aa5-2241fcf75478","url":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478","json_url":"https://onlylabs.fyi/signals/6d7906b0-6cbd-4378-8aa5-2241fcf75478/signal.json","source_url":"https://github.com/Cerebras/gigaGPT","title":"Cerebras/gigaGPT","summary":"Cerebras published a new repository. onlylabs watches repos for tooling, eval, infra, and model-adjacent work.","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2023-12-04T18:39:51+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/Cerebras/gigaGPT"]},"facets":{"repo":"Cerebras/gigaGPT","language":"Python"},"traction":{"github_stars":333,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"url":"https://github.com/Cerebras/gigaGPT","final_url":"https://github.com/Cerebras/gigaGPT","title":"Cerebras/gigaGPT repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:10:12.799786+00:00","bytes":15329,"raw_path":"2dca4284e94b0be61b31f79a86bc378bf782f222a788bed2903086dc55df6bc7.json","content_hash":"d01367521c4ba1ed7298982b55dc95a648c2406971c021b3def239315dbdfbdb","excerpt_chars":1200,"truncated":true,"excerpt":"Cerebras/gigaGPT Description: a small code base for training large models Language: Python License: Apache-2.0 Stars: 333 Forks: 46 Open issues: 3 Created: 2023-12-04T18:39:51Z Pushed: 2025-04-28T09:27:50Z Default branch: main Fork: no Archived: no README: gigaGPT ![gigaGPT](assets/boats.png) We present gigaGPT – the simplest implementation for training large language models with tens or hundreds of billions of parameters. This work was inspired by Andrej Karpathy's [nanoGPT](https://github.com/karpathy/nanoGPT/tree/master). However, while nanoGPT is designed to train medium sized models up to around the 1B parameter range, gigaGPT leverages Cerebras hardware to use a single simple model definition and training loop to scale to GPT-3 sized models run across exaflop scale clusters. See our [technical blog](https://www.cerebras.net/blog/gigaGPT) for a detailed overview. As in nanoGPT, the main training logic is split between [`train.py`](./train.py) and [`model.py`](./model.py), with a total of 565 lines of simple, readable pytorch code combined. While nanoGPT can replicate GPT-2, gigaGPT is built to be able to replicate something of the scale of GPT-3 (albeit possibly with a..."},"evidence_pages":[{"url":"https://github.com/Cerebras/gigaGPT","final_url":"https://github.com/Cerebras/gigaGPT","title":"Cerebras/gigaGPT repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:10:12.799786+00:00","bytes":15329,"raw_path":"2dca4284e94b0be61b31f79a86bc378bf782f222a788bed2903086dc55df6bc7.json","content_hash":"d01367521c4ba1ed7298982b55dc95a648c2406971c021b3def239315dbdfbdb","excerpt_chars":1200,"truncated":true,"excerpt":"Cerebras/gigaGPT Description: a small code base for training large models Language: Python License: Apache-2.0 Stars: 333 Forks: 46 Open issues: 3 Created: 2023-12-04T18:39:51Z Pushed: 2025-04-28T09:27:50Z Default branch: main Fork: no Archived: no README: gigaGPT ![gigaGPT](assets/boats.png) We present gigaGPT – the simplest implementation for training large language models with tens or hundreds of billions of parameters. This work was inspired by Andrej Karpathy's [nanoGPT](https://github.com/karpathy/nanoGPT/tree/master). However, while nanoGPT is designed to train medium sized models up to around the 1B parameter range, gigaGPT leverages Cerebras hardware to use a single simple model definition and training loop to scale to GPT-3 sized models run across exaflop scale clusters. See our [technical blog](https://www.cerebras.net/blog/gigaGPT) for a detailed overview. As in nanoGPT, the main training logic is split between [`train.py`](./train.py) and [`model.py`](./model.py), with a total of 565 lines of simple, readable pytorch code combined. While nanoGPT can replicate GPT-2, gigaGPT is built to be able to replicate something of the scale of GPT-3 (albeit possibly with a..."}],"related_signals":[{"id":"b0e6a0ff-b624-479f-bb4b-90ddab6500f5","url":"https://onlylabs.fyi/signals/b0e6a0ff-b624-479f-bb4b-90ddab6500f5","source_url":"https://github.com/Cerebras/digital_barista","title":"Cerebras/digital_barista","context":"HTML","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-01-26T18:51:05+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source"},{"id":"83e1a519-f8d3-467b-9748-12005434e863","url":"https://onlylabs.fyi/signals/83e1a519-f8d3-467b-9748-12005434e863","source_url":"https://github.com/Cerebras/spec_md_files","title":"Cerebras/spec_md_files","context":null,"kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2026-01-19T21:11:25+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source"},{"id":"cc3fa22e-55b5-4175-a6db-5aab8932761d","url":"https://onlylabs.fyi/signals/cc3fa22e-55b5-4175-a6db-5aab8932761d","source_url":"https://github.com/Cerebras/vscode-cerebras-chat","title":"Cerebras/vscode-cerebras-chat","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2025-08-30T04:15:24+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source"},{"id":"5fa521f8-0003-4f1d-9b26-ecddff27e136","url":"https://onlylabs.fyi/signals/5fa521f8-0003-4f1d-9b26-ecddff27e136","source_url":"https://github.com/Cerebras/cerebras-code-mcp","title":"Cerebras/cerebras-code-mcp","context":"JavaScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2025-08-20T21:22:51+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source"},{"id":"ca1c7fed-a8b0-484f-a81a-8088a8c376e7","url":"https://onlylabs.fyi/signals/ca1c7fed-a8b0-484f-a81a-8088a8c376e7","source_url":"https://github.com/Cerebras/Cerebras-Inference-Cookbook","title":"Cerebras/Cerebras-Inference-Cookbook","context":"Jupyter Notebook","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2025-07-08T15:59:00+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source"},{"id":"17d6bc90-2c99-4841-a35c-713b71fd990e","url":"https://onlylabs.fyi/signals/17d6bc90-2c99-4841-a35c-713b71fd990e","source_url":"https://github.com/Cerebras/exome_bench","title":"Cerebras/exome_bench","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"cerebras","name":"Cerebras","category":"neocloud"},"occurred_at":"2025-03-28T18:27:00+00:00","first_seen_at":"2026-06-05T22:32:09.055739+00:00","date_source":"source"}]}