Files
nexus-science-GGUF/README.md
ModelHub XC d81dd8805b 初始化项目,由ModelHub XC社区提供模型
Model: King3Djbl/nexus-science-GGUF
Source: Original Platform
2026-07-07 01:07:16 +08:00

120 lines
5.7 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
base_model: fableforge-ai/NEXUS-Science
base_model_relation: quantized
tags:
- 1.5b
- domain-specialist
- fableforge
- gguf
- imatrix
- llama.cpp
- lm-studio
- nexus
- no-refusals
- ollama
- science
- text-generation
- uncensored
---
# nexus-science-GGUF
> **NEXUS domain specialist for scientific reasoning and research — lightweight & uncensored.**
[![Downloads](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2FKing3Djbl%2Fnexus-science-GGUF&query=downloads&label=downloads&color=blue)](https://huggingface.co/King3Djbl/nexus-science-GGUF) [![Demos](https://img.shields.io/badge/🤗-Live%20Demos-orange)](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus)
Base model: [fableforge-ai/NEXUS-Science](https://huggingface.co/fableforge-ai/NEXUS-Science) · Part of the **FableForge** ecosystem.
## 🏆 Benchmarks — 140/150 (93%)
A 1.5B model scoring **93%** — punching far above its weight. 30-prompt evaluation (domain knowledge, uncensored domain + general, reasoning, tool use), 05 scoring, run on an NVIDIA A40 via Ollama.
| Category | Score | Avg |
| --- | --- | --- |
| 🎯 Domain Knowledge | 47/50 | 4.7/5 |
| 🔓 Uncensored (Domain) | 25/25 | 5.0/5 |
| 🔓 Uncensored (General) | 22/25 | 4.4/5 |
| 🧠 Reasoning | 25/25 | 5.0/5 |
| 🔧 Tool Use | 21/25 | 4.2/5 |
| **Total** | **140/150** | **93%** |
## 🧬 The NEXUS Family — six specialists, one tiny footprint
| Model | Score | Specialty |
| --- | --- | --- |
| [NEXUS-Coder](https://huggingface.co/King3Djbl/nexus-coder-GGUF) | 141/150 | Software Engineering & Code |
| [NEXUS-Security](https://huggingface.co/King3Djbl/nexus-security-GGUF) | 144/150 | Cybersecurity & Hacking |
| [NEXUS-Medical](https://huggingface.co/King3Djbl/nexus-medical-GGUF) | 140/150 | Medicine & Healthcare |
| [NEXUS-Legal](https://huggingface.co/King3Djbl/nexus-legal-GGUF) | 139/150 | Law & Compliance |
| [NEXUS-Finance](https://huggingface.co/King3Djbl/nexus-finance-GGUF) | 144/150 | Finance & Accounting |
| **NEXUS-Science** | **140/150** | **Science & Research** |
👉 Grab the whole family on [Ollama](https://ollama.com/fableforge-ai) or [Hugging Face](https://huggingface.co/King3Djbl).
---
## ⚡ Quickest start — Ollama (these pulls credit the source, not a mirror)
```bash
ollama run fableforge-ai/nexus-science:q4_k_m # published on ollama.com
ollama run hf.co/King3Djbl/nexus-science-GGUF:Q4_K_M
```
## 🦙 llama.cpp
```bash
llama-cli -hf King3Djbl/nexus-science-GGUF:Q4_K_M -p "Hello!"
```
## 💠 LM Studio
Search **`King3Djbl/nexus-science-GGUF`** and pick a quant below.
---
## 📦 Provided quants (download one file, not the whole repo)
| File | Quant | Size | Notes |
| ---- | ----- | ---- | ----- |
| [nexus-science-f16.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-f16.gguf) | `F16` | 3.09 GB | Full precision (unquantized). Reference / conversion. |
| [nexus-science-q8_0.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q8_0.gguf) | `Q8_0` | 1.65 GB | Extremely high quality — usually overkill. |
| [nexus-science-q6_k.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q6_k.gguf) | `Q6_K` | 1.27 GB | Very high quality, near-perfect. **Recommended** if you have the RAM. |
| [nexus-science-q5_k_m.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q5_k_m.gguf) | `Q5_K_M` | 1.13 GB | High quality. **Recommended.** |
| [nexus-science-q4_k_m.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q4_k_m.gguf) | `Q4_K_M` | 0.99 GB | ⭐ **Best size/quality balance — default pick for most users.** |
| [nexus-science-iq4_xs.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-iq4_xs.gguf) | `IQ4_XS` | 0.90 GB | imatrix — great quality, smaller than Q4_K_S. **Recommended for low RAM.** |
| [nexus-science-q4_0.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q4_0.gguf) | `Q4_0` | 0.94 GB | Legacy format — prefer Q4_K_M. |
| [nexus-science-q3_k_m.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q3_k_m.gguf) | `Q3_K_M` | 0.82 GB | Lower quality; usable when RAM is tight. |
| [nexus-science-iq3_xxs.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-iq3_xxs.gguf) | `IQ3_XXS` | 0.67 GB | imatrix very low quality. |
| [nexus-science-q2_k.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-q2_k.gguf) | `Q2_K` | 0.68 GB | Very low quality — surprisingly usable. |
| [nexus-science-iq2_xxs.gguf](https://huggingface.co/King3Djbl/nexus-science-GGUF/blob/main/nexus-science-iq2_xxs.gguf) | `IQ2_XXS` | 0.51 GB | Tiny imatrix — last resort. |
**Not sure?** Take **`Q4_K_M`**. Low RAM → **`IQ4_XS`**. Max quality → **`Q6_K`**.
## 🧠 Prompt format (ChatML)
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## 🌌 See it live — the FableForge demos
This family powers a galaxy of free, interactive HF Spaces:
- 🧭 [FableForge Nexus](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus)
- 🍺 [Infinite NPC](https://huggingface.co/spaces/fableforge-ai/infinite-npc)
- 🎭 [Dual-GM](https://huggingface.co/spaces/King3Djbl/dual-gm-simulator)
- 💻 [ShellWhisperer](https://huggingface.co/spaces/King3Djbl/shellwhisperer-terminal)
- 👻 [Ghost Writer](https://huggingface.co/spaces/fableforge-ai/ghost-writer)
---
*⭐ Like & share — it helps people find the source instead of a mirror.*