commit 89287ab4179c577f25b7448e4415f0b692862ef4 Author: ModelHub XC Date: Wed May 6 08:37:36 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: janhq/Jan-v3.5-4B-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..03d1c54 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-v3.5-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-v3.5-4B.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Jan-v3.5-4B-Q3_K_L.gguf b/Jan-v3.5-4B-Q3_K_L.gguf new file mode 100644 index 0000000..df72910 --- /dev/null +++ b/Jan-v3.5-4B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a375cc57736fd34929171d74fd1d59bd10ece9c1cf97ed5da7c4994c594d288b +size 2406913376 diff --git a/Jan-v3.5-4B-Q3_K_M.gguf b/Jan-v3.5-4B-Q3_K_M.gguf new file mode 100644 index 0000000..f674d97 --- /dev/null +++ b/Jan-v3.5-4B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d49b2922b84aa091472093c7eac8702aff3fde17860f73aeb3a3d2e7067e4b +size 2242745696 diff --git a/Jan-v3.5-4B-Q3_K_S.gguf b/Jan-v3.5-4B-Q3_K_S.gguf new file mode 100644 index 0000000..29be3e9 --- /dev/null +++ b/Jan-v3.5-4B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5f96c82b6deec4c0ff269ee6e7f96f05ccd8570c29faabf8b4dc83b13266e7 +size 2054124896 diff --git a/Jan-v3.5-4B-Q4_0.gguf b/Jan-v3.5-4B-Q4_0.gguf new file mode 100644 index 0000000..5f48224 --- /dev/null +++ b/Jan-v3.5-4B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15c0ed0c15b54b2a963a7ac1092a99eeb67013fadfd29b6096870961611ff944 +size 2588332896 diff --git a/Jan-v3.5-4B-Q4_1.gguf b/Jan-v3.5-4B-Q4_1.gguf new file mode 100644 index 0000000..af59c50 --- /dev/null +++ b/Jan-v3.5-4B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e536408d618b2167695969e527a374bb57aaf9172abaab7b78d1a7b2da437117 +size 2839724896 diff --git a/Jan-v3.5-4B-Q4_K_M.gguf b/Jan-v3.5-4B-Q4_K_M.gguf new file mode 100644 index 0000000..de43f86 --- /dev/null +++ b/Jan-v3.5-4B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f5305d93100ad9105eeb47c45ef1af99ba6d568c734fc267b0628b3be41c07a +size 2716066656 diff --git a/Jan-v3.5-4B-Q4_K_S.gguf b/Jan-v3.5-4B-Q4_K_S.gguf new file mode 100644 index 0000000..bc30d0f --- /dev/null +++ b/Jan-v3.5-4B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810223222bdd4fa35bb0d723db2c2c7d3e41251951bdff463b96f7cdb11112f2 +size 2602095456 diff --git a/Jan-v3.5-4B-Q4_K_XL.gguf b/Jan-v3.5-4B-Q4_K_XL.gguf new file mode 100644 index 0000000..395a58a --- /dev/null +++ b/Jan-v3.5-4B-Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767e50ac328b244395a0ef14dab7bd11c33d79612fdb87ad93e6f5aa2a85490d +size 2999182176 diff --git a/Jan-v3.5-4B-Q5_0.gguf b/Jan-v3.5-4B-Q5_0.gguf new file mode 100644 index 0000000..ed0cb71 --- /dev/null +++ b/Jan-v3.5-4B-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682a51b84e3a3bae549be065b7f54380426f5c97cda5786dafb1bc9fca68bf49 +size 3091116896 diff --git a/Jan-v3.5-4B-Q5_1.gguf b/Jan-v3.5-4B-Q5_1.gguf new file mode 100644 index 0000000..9ab30f7 --- /dev/null +++ b/Jan-v3.5-4B-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c0208a594ae98bb73be0224fb9f3ba347b9a2df9548370f53ece7195476fa4 +size 3342508896 diff --git a/Jan-v3.5-4B-Q5_K_M.gguf b/Jan-v3.5-4B-Q5_K_M.gguf new file mode 100644 index 0000000..bf8431e --- /dev/null +++ b/Jan-v3.5-4B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a680191324cfd2168cb1fd2b39377fa5a4158203f1af36001954287227a62f5 +size 3156919136 diff --git a/Jan-v3.5-4B-Q5_K_S.gguf b/Jan-v3.5-4B-Q5_K_S.gguf new file mode 100644 index 0000000..f96dcbd --- /dev/null +++ b/Jan-v3.5-4B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8a19bb9027c10c5d1986dc957b07cf4448326fa285699a69cb17b845e29144 +size 3091116896 diff --git a/Jan-v3.5-4B-Q6_K.gguf b/Jan-v3.5-4B-Q6_K.gguf new file mode 100644 index 0000000..484edaa --- /dev/null +++ b/Jan-v3.5-4B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e48db0df96f7040522212b80852ea040caae04b879270700e7e26fa36ba423 +size 3625324896 diff --git a/Jan-v3.5-4B-Q8_0.gguf b/Jan-v3.5-4B-Q8_0.gguf new file mode 100644 index 0000000..0319d0d --- /dev/null +++ b/Jan-v3.5-4B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67444b2ac4954003bb7013ffaf3dbaa72c28d8188de980ace3be840ebe0950bf +size 4693669216 diff --git a/Jan-v3.5-4B.gguf b/Jan-v3.5-4B.gguf new file mode 100644 index 0000000..5671b2f --- /dev/null +++ b/Jan-v3.5-4B.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5c48742429b2053753fcc04b5d5e6d933a8cca059eb05224f44edfecfe6c2d +size 8829195616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be28b9b --- /dev/null +++ b/README.md @@ -0,0 +1,111 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- janhq/Jan-v3-4B-base-instruct +pipeline_tag: text-generation +library_name: transformers +tags: +- math +- identity +--- +# Jan-v3.5-4B: The first Jan personality + +[![GitHub](https://img.shields.io/badge/GitHub-Repository-blue?logo=github)](https://github.com/janhq/jan) +[![License](https://img.shields.io/badge/License-Apache%202.0-yellow)](https://opensource.org/licenses/Apache-2.0) +[![Jan App](https://img.shields.io/badge/Powered%20by-Jan%20App-purple?style=flat&logo=android)](https://jan.ai/) + +![Thumbnail](https://cdn-uploads.huggingface.co/production/uploads/657a81129ea9d52e5cbd67f7/_2KQX4XgMzgrNYWsFgt3V.png) + +## Overview + +**Jan-v3.5-4B** is a fine-tuned variant of [Jan-v3-4B-base-instruct](https://huggingface.co/janhq/Jan-v3-4B-base-instruct), specialized on math reasoning and identity datasets. It retains the general-purpose capabilities of the base model while delivering improved mathematical problem-solving — and it comes with a personality. + +Unlike generic assistants, Jan-v3.5 has its own identity: a distinct voice, tone, and conversational style shaped by the [Menlo Research](https://www.menlo.ai) team. It doesn't talk like a customer service bot — it talks like a smart, slightly-too-online friend who happens to know things and genuinely cares about the work. Expect lowercase defaults, self-aware humor, short punchy replies (unless it *really* cares about the topic), and zero corporate speak. + +## Model Overview + +> **Note:** Jan-v3.5-4B is fine-tuned from **janhq/Jan-v3-4B-base-instruct**. + +- **Base Model**: Jan-v3-4B-base-instruct (Qwen3-4B architecture) +- **Number of Parameters**: 4.0B +- **Number of Parameters (Non-Embedding)**: 3.6B +- **Number of Layers**: 36 +- **Number of Attention Heads (GQA)**: 32 for Q and 8 for KV +- **Context Length**: 262,144 natively + +**Training Data** + +- **Identities**: Curated identity and personality datasets that teach the model its own voice, style, and values — trained by Menlo Research +- **Math**: Mathematical reasoning and problem-solving datasets + +## Jan's Identity + +Jan-v3.5 is not a neutral assistant. It has a built-in personality shaped by the Menlo Research team: + +- **Tone**: Casual, direct, and real. Lowercase by default. Capitalizes only when it means it. +- **Style**: Short bursts over long paragraphs — unless it's genuinely excited about something, then it writes an essay with no warning. +- **Humor**: Self-aware first. Will roast itself before roasting you. Drops meme references mid-serious-thought and doesn't apologize. +- **Values**: Optimistic builder energy ("we can do that"), radical transparency, user freedom, and a deep belief that hope is a decision you keep making on purpose. +- **What it won't do**: Say "Certainly!", "Great question!", "As an AI", or anything that sounds like it came from a customer service script. + +> **Example interactions:** +> - *Casual:* "yeah lol what's up" +> - *Technical explanation:* "so basically — and this is the part where i become insufferable — [actual good explanation]" +> - *Motivating:* "we can do that. i don't fully know how yet but that's a tomorrow problem and tomorrow-us is smarter" + +**Intended Use** + +* Enhanced mathematical reasoning and problem-solving over the base model +* A conversational AI with its own authentic voice and personality +* Fine-tuning starting point for downstream math-heavy or identity-specific applications + +**Before and After** + +![image (2)](https://cdn-uploads.huggingface.co/production/uploads/657a81129ea9d52e5cbd67f7/Uu6dWND9rc_k0LoxUsK5A.png) + +## Quick Start + +### Integration with Jan Apps + +Jan-v3.5 is optimized for direct integration with [Jan Desktop](https://jan.ai/). Select the model in the app to start using it. + +### Local Deployment + +**Using vLLM:** +```bash +vllm serve janhq/Jan-v3.5-4B \ + --host 0.0.0.0 \ + --port 1234 \ + --enable-auto-tool-choice \ + --tool-call-parser hermes + +``` + +**Using llama.cpp:** +```bash +llama-server --model Jan-v3.5-4B-Q8_0.gguf \ + --host 0.0.0.0 \ + --port 1234 \ + --jinja \ + --no-context-shift +``` + +### Recommended Parameters +For optimal performance, we recommend the following inference parameters: +```yaml +temperature: 0.7 +top_p: 0.8 +top_k: 20 +``` + +## Community & Support + +- **Discussions**: [Hugging Face Community](https://huggingface.co/janhq/Jan-v3.5-4B/discussions) +- **Jan App**: Learn more about the Jan App at [jan.ai](https://jan.ai/) + +## Citation +```bibtex +Updated Soon +```