# ibm-granite/granite-20b-code-base-8k

Model from Hugging Face for text generation: ibm-granite/granite-20b-code-base-8k · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/ibm-granite/granite-20b-code-base-8k
- Hosting: hosted (15 files)
- Files: 15 hosted of 17 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 15 files, 40.1 GB
- Full repo upstream: 40.1 GB
- Recommended file: 40.1 GB (9 files)
- Parameters: 20B
- Download: https://huggingbay.xyz/artifact/hf-model-ibm-granite-granite-20b-code-base-8k/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/download-plan)
- Per-file SHA-256: available for 15 of 15 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 860
- Stars: 14
- Card completeness: 96%

## Description

External Hugging Face catalog record for ibm-granite/granite-20b-code-base-8k. Task: text generation. Library: transformers. Datasets referenced by card metadata: codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA. Includes 12 model-card evaluation signals. Popularity signal at import: 1,820 downloads and 14 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Referenced datasets: codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA
- Metrics: code_eval
- Paper ids: 2405.04324
- Model-index entries: granite-20b-code-base-8k
- Evaluation signals: 12 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- MBPP: pass@1 = 43.8 (text-generation)
- MBPP+: pass@1 = 51.6 (text-generation)
- HumanEvalSynthesis(Python): pass@1 = 48.2 (text-generation)
- HumanEvalSynthesis(JavaScript): pass@1 = 50 (text-generation)
- HumanEvalSynthesis(Java): pass@1 = 59.1 (text-generation)
- HumanEvalSynthesis(Go): pass@1 = 32.3 (text-generation)
- HumanEvalSynthesis(C++): pass@1 = 40.9 (text-generation)
- HumanEvalSynthesis(Rust): pass@1 = 35.4 (text-generation)
- HumanEvalExplain(Python): pass@1 = 17.1 (text-generation)
- HumanEvalExplain(JavaScript): pass@1 = 18.3 (text-generation)

## Referenced Data

- Dataset: codeparrot/github-code-clean
- Dataset: bigcode/starcoderdata
- Dataset: open-web-math/open-web-math
- Dataset: math-ai/StackMathQA
- Paper: 2405.04324

## File Hints

- .gitattributes (1.5 KB)
- README.md (11 KB)
- config.json (644 B)
- generation_config.json (132 B)
- model-00001-of-00009.safetensors (4.6 GB) LFS
- model-00002-of-00009.safetensors (4.6 GB) LFS
- model-00003-of-00009.safetensors (4.6 GB) LFS
- model-00004-of-00009.safetensors (4.6 GB) LFS
- model-00005-of-00009.safetensors (4.6 GB) LFS
- model-00006-of-00009.safetensors (4.6 GB) LFS
- model-00007-of-00009.safetensors (4.6 GB) LFS
- model-00008-of-00009.safetensors (4.6 GB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-22T13:09:57.841Z.
- Open license detected as apache-2.0.
- Model-index metadata found for granite-20b-code-base-8k.
- Model card references dataset context: codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-ibm-granite-granite-20b-code-base-8k
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-ibm-granite-granite-20b-code-base-8k
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-ibm-granite-granite-20b-code-base-8k&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-20b-code-base-8k/decentralized-fallbacks