Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,50 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- prithivMLmods/OpenScienceReasoning-Qwen-e10
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- text-generation-inference
|
| 11 |
+
- medical
|
| 12 |
+
- science
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# **OpenScienceReasoning-Qwen-e10-GGUF**
|
| 16 |
+
|
| 17 |
+
> OpenScienceReasoning-Qwen-e10 is a high-efficiency scientific reasoning model fine-tuned from Qwen3-1.7B using the nvidia/OpenScienceReasoning-2 dataset, encompassing 10,000 curated science and math entries that strengthen analytical problem-solving, chain-of-thought exploration, and code reasoning. The model excels at hybrid symbolic-AI thinking by performing structured logic, scientific derivations, multi-language coding, and generating outputs in formats such as LaTeX, Markdown, JSON, CSV, and YAML, making it ideal for research, education, and technical documentation on mid-range GPUs and edge clusters. Optimized for STEM applications, OpenScienceReasoning-Qwen-e10 delivers robust performance for tutoring, research assistance, and structured data generation while maintaining a lightweight deployment footprint.
|
| 18 |
+
|
| 19 |
+
## Model Files
|
| 20 |
+
|
| 21 |
+
| File Name | Quant Type | File Size |
|
| 22 |
+
| - | - | - |
|
| 23 |
+
| OpenScienceReasoning-Qwen-e10.BF16.gguf | BF16 | 3.45 GB |
|
| 24 |
+
| OpenScienceReasoning-Qwen-e10.F16.gguf | F16 | 3.45 GB |
|
| 25 |
+
| OpenScienceReasoning-Qwen-e10.F32.gguf | F32 | 6.89 GB |
|
| 26 |
+
| OpenScienceReasoning-Qwen-e10.Q2_K.gguf | Q2_K | 778 MB |
|
| 27 |
+
| OpenScienceReasoning-Qwen-e10.Q3_K_L.gguf | Q3_K_L | 1 GB |
|
| 28 |
+
| OpenScienceReasoning-Qwen-e10.Q3_K_M.gguf | Q3_K_M | 940 MB |
|
| 29 |
+
| OpenScienceReasoning-Qwen-e10.Q3_K_S.gguf | Q3_K_S | 867 MB |
|
| 30 |
+
| OpenScienceReasoning-Qwen-e10.Q4_0.gguf | Q4_0 | 1.05 GB |
|
| 31 |
+
| OpenScienceReasoning-Qwen-e10.Q4_1.gguf | Q4_1 | 1.14 GB |
|
| 32 |
+
| OpenScienceReasoning-Qwen-e10.Q4_K.gguf | Q4_K | 1.11 GB |
|
| 33 |
+
| OpenScienceReasoning-Qwen-e10.Q4_K_M.gguf | Q4_K_M | 1.11 GB |
|
| 34 |
+
| OpenScienceReasoning-Qwen-e10.Q4_K_S.gguf | Q4_K_S | 1.06 GB |
|
| 35 |
+
| OpenScienceReasoning-Qwen-e10.Q5_0.gguf | Q5_0 | 1.23 GB |
|
| 36 |
+
| OpenScienceReasoning-Qwen-e10.Q5_1.gguf | Q5_1 | 1.32 GB |
|
| 37 |
+
| OpenScienceReasoning-Qwen-e10.Q5_K.gguf | Q5_K | 1.26 GB |
|
| 38 |
+
| OpenScienceReasoning-Qwen-e10.Q5_K_M.gguf | Q5_K_M | 1.26 GB |
|
| 39 |
+
| OpenScienceReasoning-Qwen-e10.Q5_K_S.gguf | Q5_K_S | 1.23 GB |
|
| 40 |
+
| OpenScienceReasoning-Qwen-e10.Q6_K.gguf | Q6_K | 1.42 GB |
|
| 41 |
+
| OpenScienceReasoning-Qwen-e10.Q8_0.gguf | Q8_0 | 1.83 GB |
|
| 42 |
+
|
| 43 |
+
## Quants Usage
|
| 44 |
+
|
| 45 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 46 |
+
|
| 47 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 48 |
+
types (lower is better):
|
| 49 |
+
|
| 50 |
+
|