58 lines
2.8 KiB
Markdown
58 lines
2.8 KiB
Markdown
|
---
|
||
|
|
datasets:
|
||
|
|
- prithivMLmods/Poseidon-Reasoning-5M
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- prithivMLmods/Poseidon-Reasoning-1.7B
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformer
|
||
|
|
tags:
|
||
|
|
- text-generation-inference
|
||
|
|
- moe
|
||
|
|
- code
|
||
|
|
- science
|
||
|
|
- biology
|
||
|
|
- chemistry
|
||
|
|
- thinking
|
||
|
|
---
|
||
|
|
|
||
|
|
# **Poseidon-Reasoning-1.7B-GGUF**
|
||
|
|
|
||
|
|
> Poseidon-Reasoning-1.7B is a general-purpose, high-efficiency reasoning model fine-tuned on Qwen3-1.7B using the Poseidon-Reasoning-5M dataset (first 70K entries). Designed for mathematical, scientific, and code-related reasoning, this model strikes a balance between structured logic and contextual fluency—ideal for domains demanding symbolic precision and algorithmic thought.
|
||
|
|
|
||
|
|
# Model Files
|
||
|
|
|
||
|
|
| File Name | Format | Size | Precision | Description |
|
||
|
|
|-----------|---------|------|-----------|-------------|
|
||
|
|
| Poseidon-Reasoning-1.7B.F32.gguf | GGUF | 6.89 GB | 32-bit Float | Full precision model, highest quality |
|
||
|
|
| Poseidon-Reasoning-1.7B.F16.gguf | GGUF | 3.45 GB | 16-bit Float | Half precision, good balance of size and quality |
|
||
|
|
| Poseidon-Reasoning-1.7B.BF16.gguf | GGUF | 3.45 GB | 16-bit BFloat | Brain floating point, optimized for inference |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q8_0.gguf | GGUF | 1.83 GB | 8-bit Quantized | High quality quantized model |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q6_K.gguf | GGUF | 1.42 GB | 6-bit Quantized | Very good quality with smaller size |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q5_K_M.gguf | GGUF | 1.26 GB | 5-bit Quantized (Medium) | Good quality, balanced compression |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q5_K_S.gguf | GGUF | 1.23 GB | 5-bit Quantized (Small) | Good quality, higher compression |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q4_K_M.gguf | GGUF | 1.11 GB | 4-bit Quantized (Medium) | Decent quality with good compression |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q4_K_S.gguf | GGUF | 1.06 GB | 4-bit Quantized (Small) | Decent quality, higher compression |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q3_K_L.gguf | GGUF | 1 GB | 3-bit Quantized (Large) | Lower quality but very compact |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q3_K_M.gguf | GGUF | 940 MB | 3-bit Quantized (Medium) | Lower quality, more compact |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q3_K_S.gguf | GGUF | 867 MB | 3-bit Quantized (Small) | Lower quality, most compact |
|
||
|
|
| Poseidon-Reasoning-1.7B.Q2_K.gguf | GGUF | 778 MB | 2-bit Quantized | Minimal quality, maximum compression |
|
||
|
|
|
||
|
|
## Configuration Files
|
||
|
|
|
||
|
|
| File Name | Size | Description |
|
||
|
|
|-----------|------|-------------|
|
||
|
|
| config.json | 29 Bytes | Model configuration parameters |
|
||
|
|
| .gitattributes | 2.44 kB | Git LFS configuration for large files |
|
||
|
|
| README.md | 288 Bytes | Project documentation |
|
||
|
|
|
||
|
|
## 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):
|
||
|
|
|
||
|
|
|