Update README.md

README.md

@@ -2,4 +2,42 @@
 license: apache-2.0
 tags:
 - 'Thinking: Disabled'
----
+- text-generation-inference
+language:
+- en
+base_model:
+- prithivMLmods/Omega-Qwen2.5-Coder-3B
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# **Omega-Qwen2.5-Coder-3B-GGUF**
+
+> Omega-Qwen2.5-Coder-3B is a compact and high-efficiency code-focused model fine-tuned on Qwen2.5-Coder-3B-Instruct, using the symbolic-rich Open-Omega-Forge-1M dataset. Designed specifically for hard-coded tasks and deterministic computation, this model runs in a "thinking-disabled" mode—delivering precise, structured outputs with minimal hallucination, making it ideal for rigorous coding workflows and embedded logic applications.
+
+## Model Files
+
+| File Name | Size | Precision |
+|-----------|------|-----------|
+| Omega-Qwen2.5-Coder-3B.BF16.gguf | 6.18 GB | BF16 |
+| Omega-Qwen2.5-Coder-3B.F16.gguf | 6.18 GB | F16 |
+| Omega-Qwen2.5-Coder-3B.F32.gguf | 12.3 GB | F32 |
+| Omega-Qwen2.5-Coder-3B.Q2_K.gguf | 1.27 GB | Q2_K |
+| Omega-Qwen2.5-Coder-3B.Q3_K_L.gguf | 1.71 GB | Q3_K_L |
+| Omega-Qwen2.5-Coder-3B.Q3_K_M.gguf | 1.59 GB | Q3_K_M |
+| Omega-Qwen2.5-Coder-3B.Q3_K_S.gguf | 1.45 GB | Q3_K_S |
+| Omega-Qwen2.5-Coder-3B.Q4_K_M.gguf | 1.93 GB | Q4_K_M |
+| Omega-Qwen2.5-Coder-3B.Q4_K_S.gguf | 1.83 GB | Q4_K_S |
+| Omega-Qwen2.5-Coder-3B.Q5_K_M.gguf | 2.22 GB | Q5_K_M |
+| Omega-Qwen2.5-Coder-3B.Q5_K_S.gguf | 2.17 GB | Q5_K_S |
+| Omega-Qwen2.5-Coder-3B.Q6_K.gguf | 2.54 GB | Q6_K |
+| Omega-Qwen2.5-Coder-3B.Q8_0.gguf | 3.29 GB | Q8_0 |
+
+## 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)