commit b259033d55336a2b8db84ab14d172f7d5d3626e7 Author: ModelHub XC Date: Thu Oct 8 12:17:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: gabriellarson/Jan-nano-128k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f999a67 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-F16.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Jan-nano-128k-F16.gguf b/Jan-nano-128k-F16.gguf new file mode 100644 index 0000000..aa23b16 --- /dev/null +++ b/Jan-nano-128k-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc346213323d40cdd19c868f38ebefcbd51f327246dba1f18a8be4272221aff4 +size 8051285120 diff --git a/Jan-nano-128k-IQ1_M.gguf b/Jan-nano-128k-IQ1_M.gguf new file mode 100644 index 0000000..4dd5e5a --- /dev/null +++ b/Jan-nano-128k-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7c20a78f9638cf13871b0da0e447a9205fbfa68b0b275b0e8474b326144843 +size 1127017856 diff --git a/Jan-nano-128k-IQ1_S.gguf b/Jan-nano-128k-IQ1_S.gguf new file mode 100644 index 0000000..43a81c1 --- /dev/null +++ b/Jan-nano-128k-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebbd42786ccde7bafefa1d95624bd8ebd9c64c02733d9be8aa0ff45eb913a9c3 +size 1055255936 diff --git a/Jan-nano-128k-IQ2_M.gguf b/Jan-nano-128k-IQ2_M.gguf new file mode 100644 index 0000000..b2e4d2b --- /dev/null +++ b/Jan-nano-128k-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23180fb7bf7e5458b45944047afb56072945dda57029b20fa88a5b1734082d7a +size 1512983936 diff --git a/Jan-nano-128k-IQ2_S.gguf b/Jan-nano-128k-IQ2_S.gguf new file mode 100644 index 0000000..eb5d1b3 --- /dev/null +++ b/Jan-nano-128k-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df96c98589d37e7ade68d9bf682a704c3210a94d09ff2476cc7c9d627b4a0136 +size 1417301376 diff --git a/Jan-nano-128k-IQ2_XS.gguf b/Jan-nano-128k-IQ2_XS.gguf new file mode 100644 index 0000000..f02b1e7 --- /dev/null +++ b/Jan-nano-128k-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1793a17a2f93b76237811642a8305b0d5f484585b1c466a71295131e99c1f70 +size 1354100096 diff --git a/Jan-nano-128k-IQ2_XXS.gguf b/Jan-nano-128k-IQ2_XXS.gguf new file mode 100644 index 0000000..5787a7a --- /dev/null +++ b/Jan-nano-128k-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481df223916016a57b5d3081308ffb296fa21f8636a53ccd531e0fcc0f115113 +size 1246621056 diff --git a/Jan-nano-128k-IQ3_M.gguf b/Jan-nano-128k-IQ3_M.gguf new file mode 100644 index 0000000..6352726 --- /dev/null +++ b/Jan-nano-128k-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd8eeb8dc2d027de75875f828d5b03222da4f53299883ebb2ece739c45b2ce0 +size 1962896256 diff --git a/Jan-nano-128k-IQ3_S.gguf b/Jan-nano-128k-IQ3_S.gguf new file mode 100644 index 0000000..fd79803 --- /dev/null +++ b/Jan-nano-128k-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f000c0efa65f88355b1550dd2192edeac4247eb5ef04e1e684b5941c14d1bd0e +size 1899531136 diff --git a/Jan-nano-128k-IQ3_XS.gguf b/Jan-nano-128k-IQ3_XS.gguf new file mode 100644 index 0000000..9c7a357 --- /dev/null +++ b/Jan-nano-128k-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae1a60f7c0f4ee260a66cd48c5b49599480901c75f34f6c8bc60a5b08612bca +size 1814375296 diff --git a/Jan-nano-128k-IQ3_XXS.gguf b/Jan-nano-128k-IQ3_XXS.gguf new file mode 100644 index 0000000..b6c3dd1 --- /dev/null +++ b/Jan-nano-128k-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba7b8b37b60dae5c116775abefb69e824867d9cd878e92a88f8cb67f04cb7d5 +size 1670188416 diff --git a/Jan-nano-128k-IQ4_XS.gguf b/Jan-nano-128k-IQ4_XS.gguf new file mode 100644 index 0000000..b99dd64 --- /dev/null +++ b/Jan-nano-128k-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df35e910890d2bc1094ab04c701dfd27db4760c23536dab615cbc454625cfa9a +size 2270751616 diff --git a/Jan-nano-128k-Q2_K.gguf b/Jan-nano-128k-Q2_K.gguf new file mode 100644 index 0000000..9a8bebf --- /dev/null +++ b/Jan-nano-128k-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dceaf99f2539ade9773153d15d9f28deab29a9ddd5f230d1b8e7622fb097eb49 +size 1669499776 diff --git a/Jan-nano-128k-Q2_K_S.gguf b/Jan-nano-128k-Q2_K_S.gguf new file mode 100644 index 0000000..f503478 --- /dev/null +++ b/Jan-nano-128k-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce9d5a5d9b9533d99cc6d0f0e72d0cbc3119a26e4a065ccc5e1e371dccd567d +size 1563454336 diff --git a/Jan-nano-128k-Q3_K_L.gguf b/Jan-nano-128k-Q3_K_L.gguf new file mode 100644 index 0000000..4c3a680 --- /dev/null +++ b/Jan-nano-128k-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f74f7e9bdbf938fe90b333870aa5e4403fa95efa5fd805de88785edafa8da0d +size 2239785856 diff --git a/Jan-nano-128k-Q3_K_M.gguf b/Jan-nano-128k-Q3_K_M.gguf new file mode 100644 index 0000000..1e2ed90 --- /dev/null +++ b/Jan-nano-128k-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83af3008aff1393410b96b7be4d3a7d01ccc1426659b3a484992b9561e262f1 +size 2075618176 diff --git a/Jan-nano-128k-Q3_K_S.gguf b/Jan-nano-128k-Q3_K_S.gguf new file mode 100644 index 0000000..b7a73ed --- /dev/null +++ b/Jan-nano-128k-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40059e01cdf493143de462115c773f2d9e387c9ffb531e11ee29ba721d5882c6 +size 1886997376 diff --git a/Jan-nano-128k-Q4_0.gguf b/Jan-nano-128k-Q4_0.gguf new file mode 100644 index 0000000..a573c30 --- /dev/null +++ b/Jan-nano-128k-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd19984b257e245ec6121b0ce7e0103f79851dd5e6f88fe4f5c957da48507086 +size 2375773056 diff --git a/Jan-nano-128k-Q4_K_M.gguf b/Jan-nano-128k-Q4_K_M.gguf new file mode 100644 index 0000000..9cf9713 --- /dev/null +++ b/Jan-nano-128k-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2de6f72d472602c9fcbda199a9090176be674ee2b6c95f1b9f63f7288230f3c +size 2497280896 diff --git a/Jan-nano-128k-Q4_K_S.gguf b/Jan-nano-128k-Q4_K_S.gguf new file mode 100644 index 0000000..848970e --- /dev/null +++ b/Jan-nano-128k-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49429ad4ea61442a3fbd65d8743e9696e5a6eb508bdd41df95ea7050a4ddeb25 +size 2383309696 diff --git a/Jan-nano-128k-Q5_0.gguf b/Jan-nano-128k-Q5_0.gguf new file mode 100644 index 0000000..046d957 --- /dev/null +++ b/Jan-nano-128k-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a2396feeb6f0efccf7eaf4495096ef7cbfd73892f5feb24f98ada2e3b7b988 +size 2829937536 diff --git a/Jan-nano-128k-Q5_K_M.gguf b/Jan-nano-128k-Q5_K_M.gguf new file mode 100644 index 0000000..c1d1181 --- /dev/null +++ b/Jan-nano-128k-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35dfd42be61144e9bb660cb9cee89a113516cabf947a172965ac0f2169344e5 +size 2889513856 diff --git a/Jan-nano-128k-Q5_K_S.gguf b/Jan-nano-128k-Q5_K_S.gguf new file mode 100644 index 0000000..77e62a8 --- /dev/null +++ b/Jan-nano-128k-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1c356114cf9b38ba7e2898d44b3fbd1dbeb6bcb2c81487acb5026ab344ba0c +size 2823711616 diff --git a/Jan-nano-128k-Q6_K.gguf b/Jan-nano-128k-Q6_K.gguf new file mode 100644 index 0000000..64fb69c --- /dev/null +++ b/Jan-nano-128k-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630469b634ba5e1e9512dd81c4c805c250d68e69fb0c3b801dadb728154c5e99 +size 3306261376 diff --git a/Jan-nano-128k-Q8_0.gguf b/Jan-nano-128k-Q8_0.gguf new file mode 100644 index 0000000..05a76d1 --- /dev/null +++ b/Jan-nano-128k-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701664fdc926e46aa2ba2338e5534c150c2c4e77505ba0dca759c27ab411a80c +size 4280405376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34c5303 --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Menlo/Jan-nano-128k +pipeline_tag: text-generation +--- +# Jan-Nano-128k: Empowering deeper research through extended context understanding. + +[![GitHub](https://img.shields.io/badge/GitHub-Repository-blue?logo=github)](https://github.com/menloresearch/deep-research) +[![License](https://img.shields.io/badge/License-Apache%202.0-yellow)](https://opensource.org/licenses/Apache-2.0) + +
+ Jan-Nano-128k +
+ +**Authors:** [Alan Dao](https://scholar.google.com/citations?user=eGWws2UAAAAJ&hl=en), [Bach Vu Dinh](https://scholar.google.com/citations?user=7Lr6hdoAAAAJ&hl=vi), [Thinh Le](https://scholar.google.com/citations?user=8tcN7xMAAAAJ&hl=en) + +## Overview + +Jan-Nano-128k represents a significant advancement in compact language models for research applications. Building upon the success of [Jan-Nano](https://huggingface.co/Menlo/Jan-nano), this enhanced version features a **native 128k context window** that enables deeper, more comprehensive research capabilities without the performance degradation typically associated with context extension methods. + +**Key Improvements:** +- **🔍 Research Deeper**: Extended context allows for processing entire research papers, lengthy documents, and complex multi-turn conversations +- **⚡ Native 128k Window**: Built from the ground up to handle long contexts efficiently, maintaining performance across the full context range +- **📈 Enhanced Performance**: Unlike traditional context extension methods, Jan-Nano-128k shows improved performance with longer contexts + +This model maintains full compatibility with Model Context Protocol (MCP) servers while dramatically expanding the scope of research tasks it can handle in a single session. + +## Evaluation + +Jan-Nano-128k has been rigorously evaluated on the SimpleQA benchmark using our MCP-based methodology, demonstrating superior performance compared to its predecessor: + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/Bc0ehij86l_NX52OfxeOj.png) + +## Why Jan-Nano-128k? + +Traditional approaches to extending context length, such as YaRN (Yet another RoPE extensioN), often result in performance degradation as context length increases. Jan-Nano-128k breaks this paradigm: + +This fundamental difference makes Jan-Nano-128k ideal for research applications requiring deep document analysis, multi-document synthesis, and complex reasoning over large information sets. + +## 🖥️ How to Run Locally + +![Jan-Nano Demo](replay.gif) + +Jan-Nano-128k is fully supported by [Jan - beta build](https://www.jan.ai/docs/desktop/beta), providing a seamless local AI experience with complete privacy and control. + +For additional tutorials and community guidance, visit our [Discussion Forums](https://huggingface.co/Menlo/Jan-nano-128k/discussions). + +### VLLM Deployment + +```bash +vllm serve Menlo/Jan-nano-128k \ + --host 0.0.0.0 \ + --port 1234 \ + --enable-auto-tool-choice \ + --tool-call-parser hermes \ + --rope-scaling '{"rope_type":"yarn","factor":3.2,"original_max_position_embeddings":40960}' --max-model-len 131072 +``` + +**Note:** The chat template is included in the tokenizer. For troubleshooting, download the [Non-think chat template](https://qwen.readthedocs.io/en/latest/_downloads/c101120b5bebcc2f12ec504fc93a965e/qwen3_nonthinking.jinja). + +### Recommended Sampling Parameters + +```yaml +Temperature: 0.7 +Top-p: 0.8 +Top-k: 20 +Min-p: 0.0 +``` + +## 🤝 Community & Support + +- **Discussions**: [HuggingFace Community](https://huggingface.co/Menlo/Jan-nano-128k/discussions) +- **Issues**: [GitHub Repository](https://github.com/menloresearch/deep-research/issues) +- **Documentation**: [Official Docs](https://menloresearch.github.io/deep-research/) + +## 📄 Citation + +```bibtex +@model{jan-nano-128k, + title={Jan-Nano-128k: Deep Research with Extended Context}, + author={Dao, Alan and Dinh, Bach Vu and Le Thinh}, + year={2024}, + url={https://huggingface.co/Menlo/Jan-nano-128k} +} +``` + +--- + +*Jan-Nano-128k: Empowering deeper research through extended context understanding.* \ No newline at end of file