# gradientai/Llama-3-8B-Instruct-Gradient-1048k This model is an instruction tuned 8B language model whose context length was extended from 8k to more than 1040K tokens. It was trained in progressive stages on increasing context lengths and on data built from SlimPajama plus a chat dataset based on UltraChat. ## Cite this - Page: https://huggingbay.xyz/artifact/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k - Citation: gradientai/Llama-3-8B-Instruct-Gradient-1048k. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k (retrieved 2026-11-15). - Check a downloaded file: run `shasum -a 256 ` (macOS), `sha256sum ` (Linux) or `Get-FileHash -Algorithm SHA256 ` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/files?limit=100. How checks work: https://huggingbay.xyz/verification ## Facts - Type: LLM - Task: text-generation - Framework: transformers - License: llama3: Commercial use is permitted with obligations: Llama community license: commercial use allowed; if your products/services exceeded 700 million monthly active users (Section 2, Additional Commercial Terms) you must request a license from Meta first; the acceptable-use policy and attribution notice apply. (https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k/blob/main/License) - Source: https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k - Hosting: hosted (11 files) - Files: 11 hosted of 13 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: 11 hosted of 13 listed - Full repo upstream: 16.1 GB - Recommended file: 16.1 GB (4 files) - Parameters: 8B - Download: https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/download-plan) - Per-file SHA-256: available for 11 of 11 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/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: 42408 - Stars: 683 - Card completeness: 92% ## Description This model is an instruction tuned 8B language model whose context length was extended from 8k to more than 1040K tokens. It was trained in progressive stages on increasing context lengths and on data built from SlimPajama plus a chat dataset based on UltraChat. ## Model Card Facts - Declared license: llama3 - Pipeline: text-generation - Library: transformers - Task categories: text-generation - Languages: en - Paper ids: 2309.00071, 2402.08268, 2305.14233 - File hints: 13 upstream file samples ## Referenced Data - Paper: 2309.00071 - Paper: 2402.08268 - Paper: 2305.14233 ## File Hints - .gitattributes (1.5 KB) - License (7.6 KB) - README.md (31 KB) - config.json (719 B) - generation_config.json (194 B) - model-00001-of-00004.safetensors (4.6 GB) LFS - model-00002-of-00004.safetensors (4.7 GB) LFS - model-00003-of-00004.safetensors (4.6 GB) LFS - model-00004-of-00004.safetensors (1.1 GB) LFS - model.safetensors.index.json (23 KB) - special_tokens_map.json (301 B) - tokenizer.json (8.7 MB) ## Quality Checklist - Summary: passed - Description: passed - Model card metadata: passed - License: review - 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 2026-09-21T06:56:28.816Z. - Upstream license: llama3. 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-gradientai-llama-3-8b-instruct-gradient-1048k - Files API: https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/files?limit=100 - Metadata: https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/metadata.json - Distribution: https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/distribution - Manifest: https://huggingbay.xyz/api/manifests/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k - Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/download-plan - Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-gradientai-llama-3-8b-instruct-gradient-1048k&limit=100 - Request mirror: not applicable. - Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-gradientai-llama-3-8b-instruct-gradient-1048k/decentralized-fallbacks