{"id":40665129,"url":"https://github.com/pythoncrazy/jimm","last_synced_at":"2026-01-21T09:07:57.620Z","repository":{"id":299517820,"uuid":"996595043","full_name":"pythoncrazy/jimm","owner":"pythoncrazy","description":"JAX Image Modeling of Models contains Computer Vision/Vision Language Model implementations in native flax nnx with proper sharding annotations (allowing you to do easy fully sharded data parallel training with native flax nnx/jax)","archived":false,"fork":false,"pushed_at":"2026-01-19T21:19:50.000Z","size":22896,"stargazers_count":5,"open_issues_count":5,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-01-20T01:05:54.950Z","etag":null,"topics":["computer-vision","flax","jax","machine-learning"],"latest_commit_sha":null,"homepage":"https://pythoncrazy.github.io/jimm/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pythoncrazy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-06-05T07:11:31.000Z","updated_at":"2026-01-19T20:50:01.000Z","dependencies_parsed_at":"2025-08-31T02:20:37.468Z","dependency_job_id":"4fd7a485-da2a-4329-ac77-b51ea2b59efa","html_url":"https://github.com/pythoncrazy/jimm","commit_stats":null,"previous_names":["pythoncrazy/jimm","locamage/jimm"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/pythoncrazy/jimm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythoncrazy%2Fjimm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythoncrazy%2Fjimm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythoncrazy%2Fjimm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythoncrazy%2Fjimm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pythoncrazy","download_url":"https://codeload.github.com/pythoncrazy/jimm/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pythoncrazy%2Fjimm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28630940,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T04:47:28.174Z","status":"ssl_error","status_checked_at":"2026-01-21T04:47:22.943Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","flax","jax","machine-learning"],"created_at":"2026-01-21T09:07:57.012Z","updated_at":"2026-01-21T09:07:57.601Z","avatar_url":"https://github.com/pythoncrazy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Jax Image Modeling of Models (jimm)\nDocs are at: [https://pythoncrazy.github.io/jimm](https://pythoncrazy.github.io/jimm)\n- This aims to be the jax counterpart to timm, with the exception that for image-text models (CLIP, SigLIP, etc), we support the text model entirely.\n- Made with flax nnx, supports weight loading from pytorch_model.bin and safetensors (as well as both methods from huggingface).\n\nModels Supported:\n- Vision Transformers\n    - Both with a classification linear layer, or not\n    - Using a CLS Token for pooling, or using Multihead Attention Pooling\n    - Can load any standard variant of Vision Transformers of any size/resolution(e.g. \"google/vit-base-patch16-224\" or \"google/vit-large-patch16-384\")\n- CLIP\n    - Can load from any checkpoints of the clip model on github (such as \"openai/clip-vit-base-patch32\" or \"geolocal/StreetCLIP\")\n- SigLIP\n    - Can load any non-naflex version of the SigLIP model, from both siglipv1 and siglipv2 (eg \"google/siglip-base-patch16-256\" or \"google/siglip2-large-patch16-512\" from huggingface or locally)\n## Installation\n### Using pixi.sh:\n`pixi add jimm@https://github.com/pythoncrazy/jimm.git --pypi`\n### Using uv\n`uv add --dev git+https://github.com/pythoncrazy/jimm.git`\nor if you prefer to not add as a direct dependency:\n`uv pip install git+https://github.com/pythoncrazy/jimm.git`\n### Using pip/conda\n`pip install git+https://github.com/pythoncrazy/jimm.git`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpythoncrazy%2Fjimm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpythoncrazy%2Fjimm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpythoncrazy%2Fjimm/lists"}