prithivMLmods's picture
Update README.md
aab96e2 verified
metadata
license: apache-2.0
language:
  - en
base_model:
  - prithivMLmods/Procyon-1.5B-Qwen2-Theorem
pipeline_tag: text-generation
library_name: transformers
tags:
  - text-generation-inference
  - theorem

Procyon-1.5B-Qwen2-Theorem-GGUF

Procyon-1.5B-Qwen2-Theorem is an experimental theorem explanation model fine-tuned on Qwen2-1.5B. Specially crafted for mathematical theorem understanding, structured concept breakdowns, and non-reasoning based explanation tasks, it targets domains where clarity and formal structure take precedence over freeform reasoning.

Model Files

File Name Size Format Description
Procyon-1.5B-Qwen2-Theorem.F32.gguf 7.11 GB F32 Full precision 32-bit floating point
Procyon-1.5B-Qwen2-Theorem.F16.gguf 3.56 GB F16 Half precision 16-bit floating point
Procyon-1.5B-Qwen2-Theorem.BF16.gguf 3.56 GB BF16 Brain floating point 16-bit
Procyon-1.5B-Qwen2-Theorem.Q8_0.gguf 1.89 GB Q8_0 8-bit quantized
Procyon-1.5B-Qwen2-Theorem.Q6_K.gguf 1.46 GB Q6_K 6-bit quantized
Procyon-1.5B-Qwen2-Theorem.Q5_K_M.gguf 1.29 GB Q5_K_M 5-bit quantized, medium quality
Procyon-1.5B-Qwen2-Theorem.Q5_K_S.gguf 1.26 GB Q5_K_S 5-bit quantized, small quality
Procyon-1.5B-Qwen2-Theorem.Q4_K_M.gguf 1.12 GB Q4_K_M 4-bit quantized, medium quality
Procyon-1.5B-Qwen2-Theorem.Q4_K_S.gguf 1.07 GB Q4_K_S 4-bit quantized, small quality
Procyon-1.5B-Qwen2-Theorem.Q3_K_L.gguf 980 MB Q3_K_L 3-bit quantized, large quality
Procyon-1.5B-Qwen2-Theorem.Q3_K_M.gguf 924 MB Q3_K_M 3-bit quantized, medium quality
Procyon-1.5B-Qwen2-Theorem.Q3_K_S.gguf 861 MB Q3_K_S 3-bit quantized, small quality
Procyon-1.5B-Qwen2-Theorem.Q2_K.gguf 753 MB Q2_K 2-bit quantized

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