# deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

This model is a 16B mixture of experts code language model with 2.4B active parameters and a 128K context length. It is the instruct variant in the Lite series and is described for code and math tasks.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct
- Citation: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct (retrieved 2026-11-13).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: deepseek-license
- Source: unknown
- Hosting: hosted (9 files)
- Files: 9 hosted of 14 listed
- Needs its own code to run: Uses custom model code (configuration_deepseek.py). Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is 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: 9 hosted of 14 listed
- Full repo upstream: 31.4 GB
- Recommended file: 31.4 GB (4 files)
- Download: https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/download-plan)
- Per-file SHA-256: available for 9 of 9 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/files?limit=100
- Availability: Ready
- Downloadable: yes
- 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: 908249
- Stars: 660
- Card completeness: 89%

## Description

This model is a 16B mixture of experts code language model with 2.4B active parameters and a 128K context length. It is the instruct variant in the Lite series and is described for code and math tasks.

## Model Card Facts

- Declared license: other
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Paper ids: 2401.06066
- File hints: 14 upstream file samples

## Referenced Data

- Paper: 2401.06066

## File Hints

- .gitattributes (1.5 KB)
- README.md (11 KB)
- config.json (1.5 KB)
- configuration_deepseek.py (10 KB)
- generation_config.json (181 B)
- model-00001-of-000004.safetensors (8.0 GB) LFS
- model-00002-of-000004.safetensors (8.0 GB) LFS
- model-00003-of-000004.safetensors (8.0 GB) LFS
- model-00004-of-000004.safetensors (5.2 GB) LFS
- model.safetensors.index.json (469 KB)
- modeling_deepseek.py (77 KB)
- tokenization_deepseek_fast.py (1.3 KB)

## Quality Checklist

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

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-20T02:37:49.536Z.
- Upstream license: other. Mirror admission policy: permissive (owner policy; no license rights inferred).
- 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-deepseek-ai-deepseek-coder-v2-lite-instruct
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-deepseek-ai-deepseek-coder-v2-lite-instruct/decentralized-fallbacks