初始化项目，由ModelHub XC社区提供模型

Model: digitranslab/Megamind-nano-128k-gguf Source: Original Platform
2026-09-25 14:23:18 +08:00
commit f9b7334b79
26 changed files with 234 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,63 @@
+*.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
+Megamind-nano-128k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Megamind-nano-128k-iQ4_XS.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-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+jan-nano-128k-Q4_1.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_0.gguf filter=lfs diff=lfs merge=lfs -text
+jan-nano-128k-Q5_1.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
+jan-nano-128k-iQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Megamind-nano-128k-Q3_K_L.gguf
+++ b/Megamind-nano-128k-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d735ebd6e6eed63eabf207f72bddadab040177a34fff2f0db15ad1566b4361a7
+size 2239785600
--- a/Megamind-nano-128k-Q3_K_M.gguf
+++ b/Megamind-nano-128k-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5104517fac344c0823b85f4055be16c61f3bab42b20321b96e9dfaa5945a0cb
+size 2075617920
--- a/Megamind-nano-128k-Q3_K_S.gguf
+++ b/Megamind-nano-128k-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0ede01db1e43310cdf1083fd48947e1cf827ce84d9a56fbbaefb05db0b66a9
+size 1886997120
--- a/Megamind-nano-128k-Q4_0.gguf
+++ b/Megamind-nano-128k-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd31a2a308c7d7e1775fc5aebf872dbacf923542b77a049ccb3f6485d5d5dcb6
+size 2369546880
--- a/Megamind-nano-128k-Q4_1.gguf
+++ b/Megamind-nano-128k-Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9220f32bee7b0b15ea5d4fdc09d10202b5305502f0c4418f6e9050807132969
+size 2596629120
--- a/Megamind-nano-128k-Q4_K_M.gguf
+++ b/Megamind-nano-128k-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78204c1789849875b2382fe10c73bc36e95ecffa6c45e5edc49548be9a79f367
+size 2497280640
--- a/Megamind-nano-128k-Q4_K_S.gguf
+++ b/Megamind-nano-128k-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81397e5b210c2bc3bb94e8c39eb194b3ea65370c769ca9467fc3353117d6ca3
+size 2383309440
--- a/Megamind-nano-128k-Q5_0.gguf
+++ b/Megamind-nano-128k-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8e587e99a8653d3c5291adfb9981d19b167429c5a9ec4a87a951cf430a83b3
+size 2823711360
--- a/Megamind-nano-128k-Q5_1.gguf
+++ b/Megamind-nano-128k-Q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a428d033a34e9987e0c044e1c97168a0bf73bdc412a18b4e018bffa766d23a
+size 3050793600
--- a/Megamind-nano-128k-Q5_K_M.gguf
+++ b/Megamind-nano-128k-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9ed13924b956da1acccd6d49f5ed6867f27a6b8f6da9b1f147b2138c66367d
+size 2889513600
--- a/README.md
+++ b/README.md
@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+language:
+- en
+base_model: digitranslab/Megamind-nano-128k
+base_model_relation: quantized
+pipeline_tag: text-generation
+---
+
+# Jan-Nano-128k: Empowering deeper research through extended context understanding.
+<sub>*Note: Jan-Nano is a non-thinking model.*</sub>
+
+
+<div align="center">
+</div>
+
+**Authors:** [Alan Dao](https://scholar.google.com/citations?user=eGWws2UAAAAJ&hl=en), [Bach Vu Dinh](https://scholar.google.com/citations?user=7Lr6hdoAAAAJ&hl=vi)
+
+## 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/digitranslab/Megamind-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:
+
+
+### 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 desktop will eventually support this model (WIP). Otherwise you can check the deployment options below that we have tested.
+
+For additional tutorials and community guidance, visit our [Discussion Forums](https://huggingface.co/digitranslab/Megamind-nano-128k/discussions).
+
+### Deployment
+
+Deploy using VLLM:
+```bash
+vllm serve digitranslab/Megamind-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
+```
+
+Or `llama-server` from `llama.cpp`:
+```bash
+llama-server ... --rope-scaling yarn --rope-scale 3.2 --yarn-orig-ctx 40960
+```
+**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
+```
+
+## FAQ:
+- I have Jinja template issue with LMStudio, how can i fix? [Here](https://huggingface.co/digitranslab/Megamind-nano-128k-gguf/discussions/1#6862fe2375cb85f79b28d69c)
+
+## 🤝 Community & Support
+
+- **Discussions**: [HuggingFace Community](https://huggingface.co/digitranslab/Megamind-nano-128k/discussions)
+- **Issues**: [GitHub Repository](https://github.com/menloresearch/jan/issues)
+- **Documentation**: [Official Docs](https://menloresearch.github.io/deep-research/)
+
+## 📄 Citation
+
+```bibtex
+@misc{dao2025jannanotechnicalreport,
+      title={Megamind-nano Technical Report}, 
+      author={Alan Dao and Dinh Bach Vu},
+      year={2025},
+      eprint={2506.22760},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2506.22760}, 
+}
+```
+
+---
+
+*Jan-Nano-128k: Empowering deeper research through extended context understanding.*
--- a/jan-nano-128k-Q3_K_L.gguf
+++ b/jan-nano-128k-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d735ebd6e6eed63eabf207f72bddadab040177a34fff2f0db15ad1566b4361a7
+size 2239785600
--- a/jan-nano-128k-Q3_K_M.gguf
+++ b/jan-nano-128k-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5104517fac344c0823b85f4055be16c61f3bab42b20321b96e9dfaa5945a0cb
+size 2075617920
--- a/jan-nano-128k-Q3_K_S.gguf
+++ b/jan-nano-128k-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0ede01db1e43310cdf1083fd48947e1cf827ce84d9a56fbbaefb05db0b66a9
+size 1886997120
--- a/jan-nano-128k-Q4_0.gguf
+++ b/jan-nano-128k-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd31a2a308c7d7e1775fc5aebf872dbacf923542b77a049ccb3f6485d5d5dcb6
+size 2369546880
--- a/jan-nano-128k-Q4_1.gguf
+++ b/jan-nano-128k-Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9220f32bee7b0b15ea5d4fdc09d10202b5305502f0c4418f6e9050807132969
+size 2596629120
--- a/jan-nano-128k-Q4_K_M.gguf
+++ b/jan-nano-128k-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78204c1789849875b2382fe10c73bc36e95ecffa6c45e5edc49548be9a79f367
+size 2497280640
--- a/jan-nano-128k-Q4_K_S.gguf
+++ b/jan-nano-128k-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81397e5b210c2bc3bb94e8c39eb194b3ea65370c769ca9467fc3353117d6ca3
+size 2383309440
--- a/jan-nano-128k-Q5_0.gguf
+++ b/jan-nano-128k-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8e587e99a8653d3c5291adfb9981d19b167429c5a9ec4a87a951cf430a83b3
+size 2823711360
--- a/jan-nano-128k-Q5_1.gguf
+++ b/jan-nano-128k-Q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a428d033a34e9987e0c044e1c97168a0bf73bdc412a18b4e018bffa766d23a
+size 3050793600
--- a/jan-nano-128k-Q5_K_M.gguf
+++ b/jan-nano-128k-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9ed13924b956da1acccd6d49f5ed6867f27a6b8f6da9b1f147b2138c66367d
+size 2889513600
--- a/jan-nano-128k-Q5_K_S.gguf
+++ b/jan-nano-128k-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4a99d0c4ed1e4e49f602a9d337b5282733ca814bac870da767cbbfc8c81ee8
+size 2823711360
--- a/jan-nano-128k-Q6_K.gguf
+++ b/jan-nano-128k-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7a3e8e6aa5a65e9e5d64753c0dcc15802bb724ca19ed18b9ab7836cb51fe30
+size 3306261120
--- a/jan-nano-128k-Q8_0.gguf
+++ b/jan-nano-128k-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a69d59a79dadfad60c2e029cd8172de09286833951afe319ab554272e153b5c
+size 4280405120
--- a/jan-nano-128k-iQ4_XS.gguf
+++ b/jan-nano-128k-iQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38768d1a6431f0eb6f77d40017f5e566a170c390c2685b23a9a9b08d7c9d981a
+size 2270751648