prithivMLmods/Eta-Aurigae-0.6B-Echelon1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: prithivMLmods/Eta-Aurigae-0.6B-Echelon1-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-04 04:45:13 +08:00
commit c97ae121e8
9 changed files with 103 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
README.md Normal file
View File

@@ -0,0 +1,37 @@
---
license: apache-2.0
language:
- en
base_model:
- prithivMLmods/Eta-Aurigae-0.6B-Echelon1
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
- science
---
# **Eta-Aurigae-0.6B-Echelon1-GGUF**
> **Eta-Aurigae-0.6B-Echelon1** is a compact, efficient model specialized in **science, factual accuracy**, and **structured reasoning**. Fine-tuned on **Qwen3-0.6B** using the **MoT (Mixture of Thoughts)** dataset—focused on scientific understanding and expert factual domains—it delivers high-precision outputs for STEM education, tutoring, and analytical thinking in resource-constrained environments.
## Model File
| File Name | Size | Format | Description |
|--------------------------------------------|--------|---------------|------------------------------------------|
| Eta-Aurigae-0.6B-Echelon1.BF16.gguf | 1.2 GB | GGUF (BF16) | BFloat16 precision model file |
| Eta-Aurigae-0.6B-Echelon1.F32.gguf | 2.39 GB| GGUF (F32) | Float32 precision model file |
| Eta-Aurigae-0.6B-Echelon1.Q4_K_M.gguf | 397 MB | GGUF (Q4_K_M) | 4-bit quantized model file |
| Eta-Aurigae-0.6B-Echelon1.Q5_K_M.gguf | 444 MB | GGUF (Q5_K_M) | 5-bit quantized model file |
| Eta-Aurigae-0.6B-Echelon1.Q8_0.gguf | 639 MB | GGUF (Q8_0) | 8-bit quantized model file |
| config.json | 31 B | JSON | Configuration file |
| .gitattributes | 1.88 kB| Text | Git attributes configuration |
## Quants Usage
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)