Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,43 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- prithivMLmods/Megatron-Bots-1.7B-Reasoning
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- text-generation-inference
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# **Megatron-Bots-1.7B-Reasoning-GGUF**
|
| 14 |
+
|
| 15 |
+
> **Megatron-Bots-1.7B-Reasoning** is a **logical reasoning and general-purpose thinking model** fine-tuned from **Qwen3-1.7B**, specifically designed for **advanced reasoning tasks and analytical problem-solving**. Built with data entries from the **SynLogic Dataset**, it excels at structured thinking, logical deduction, and comprehensive problem analysis in a compact yet powerful architecture.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Files
|
| 19 |
+
|
| 20 |
+
| File Name | Size | Format | Description |
|
| 21 |
+
|-----------|------|--------|-------------|
|
| 22 |
+
| Megatron-Bots-1.7B-Reasoning.F32.gguf | 6.89 GB | F32 | Full precision 32-bit floating point |
|
| 23 |
+
| Megatron-Bots-1.7B-Reasoning.F16.gguf | 3.45 GB | F16 | Half precision 16-bit floating point |
|
| 24 |
+
| Megatron-Bots-1.7B-Reasoning.BF16.gguf | 3.45 GB | BF16 | Brain floating point 16-bit |
|
| 25 |
+
| Megatron-Bots-1.7B-Reasoning.Q8_0.gguf | 1.83 GB | Q8_0 | 8-bit quantized |
|
| 26 |
+
| Megatron-Bots-1.7B-Reasoning.Q6_K.gguf | 1.42 GB | Q6_K | 6-bit quantized |
|
| 27 |
+
| Megatron-Bots-1.7B-Reasoning.Q5_K_M.gguf | 1.26 GB | Q5_K_M | 5-bit quantized, medium quality |
|
| 28 |
+
| Megatron-Bots-1.7B-Reasoning.Q5_K_S.gguf | 1.23 GB | Q5_K_S | 5-bit quantized, small quality |
|
| 29 |
+
| Megatron-Bots-1.7B-Reasoning.Q4_K_M.gguf | 1.11 GB | Q4_K_M | 4-bit quantized, medium quality |
|
| 30 |
+
| Megatron-Bots-1.7B-Reasoning.Q4_K_S.gguf | 1.06 GB | Q4_K_S | 4-bit quantized, small quality |
|
| 31 |
+
| Megatron-Bots-1.7B-Reasoning.Q3_K_L.gguf | 1 GB | Q3_K_L | 3-bit quantized, large quality |
|
| 32 |
+
| Megatron-Bots-1.7B-Reasoning.Q3_K_M.gguf | 940 MB | Q3_K_M | 3-bit quantized, medium quality |
|
| 33 |
+
| Megatron-Bots-1.7B-Reasoning.Q3_K_S.gguf | 867 MB | Q3_K_S | 3-bit quantized, small quality |
|
| 34 |
+
| Megatron-Bots-1.7B-Reasoning.Q2_K.gguf | 778 MB | Q2_K | 2-bit quantized |
|
| 35 |
+
|
| 36 |
+
## Quants Usage
|
| 37 |
+
|
| 38 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 39 |
+
|
| 40 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 41 |
+
types (lower is better):
|
| 42 |
+
|
| 43 |
+
|