Open-weight model
vigyan-olmo2-7b-quad-master
by Shreyansh singh shreyansh12183/vigyan-olmo2-7b-quad-master
vigyan-olmo2-7b-quad-master is an open-weight model from Shreyansh singh, released under Creative Commons Attribution-NonCommercial 4.0. It has 7.3B parameters and a 4,096-token context. At 16-bit it needs about 17.5 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Sovereign DARE-TIES Merged & DPO-Aligned Multi-Disciplinary SLM License: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (Strictly Private ) Tested against 100 completely unseen frontier Ph.D. and Olympiad examination problems: 1.
Runs On
What it takes to serve vigyan-olmo2-7b-quad-master (7.3B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 14.6 GB | 17.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.3 GB | 8.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 3.6 GB | 4.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
vigyan-olmo2-7b-quad-master on every accelerator the SAVRN Index prices, at every precision
Model Card
Sovereign DARE-TIES Merged & DPO-Aligned Multi-Disciplinary SLM License: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (Strictly Private ) Tested against 100 completely unseen frontier Ph.D. and Olympiad examination problems: 1. DARE-TIES Weight Delta Fusion: Merged 4 specialized domain LoRA adapters (phd-pure-math, silicon-rtl-eda, astro-logic, biomed-chem) into base parameters without catastrophic interference. 2. Dynamic DPO Alignment: Aligned on shreyansh12183/vigyan-gen2-7b-alignment-dataset with strict negative prompt loss masking. 3. 100% Offline Edge Ready: Quantized to Q4KM (~4.3 GB) for air-gapped workstations and defense labs.
Excerpt from the card by Shreyansh singh, licensed cc-by-nc-4.0.
Configuration
- Architecture
- Olmo2ForCausalLM
- Context length (tokens)
- 4,096
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 11,008
- Attention heads
- 32
- Key/value heads
- 32
- Vocabulary size
- 100,352
- Model type
- olmo2
Identity and Version
- Repository
- shreyansh12183/vigyan-olmo2-7b-quad-master
- Publisher
- Shreyansh singh
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 7.3B parameters
- Languages
- dpo
- Revision
- e7399b5fe61bc460143357a915f6dadba5cc2a2b
- First published
- 2026-10-07
- Last updated
- 2026-10-08
Files and Weights
19 files, 19.2 GB in total. The weights are 6 files totalling 19.1 GB in gguf, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_adapter_model.safetensors | Weights | 80.0 MB | fe4a35a27280 |
| model-00001-of-00004.safetensors | Weights | 4.0 GB | 007d4019a8b6 |
| model-00002-of-00004.safetensors | Weights | 3.9 GB | 6abc20037594 |
| model-00003-of-00004.safetensors | Weights | 4.0 GB | fd51e9465b82 |
| model-00004-of-00004.safetensors | Weights | 2.7 GB | c7fdaa5a1dd1 |
| vigyan-7b-quad-master-q4_k_m.gguf | Weights | 4.5 GB | 3d53995f4195 |
| adapter_adapter_config.json | Configuration | 1.2 KB | — |
| config.json | Configuration | 676 B | — |
| generation_config.json | Configuration | 121 B | — |
| model.safetensors.index.json | Configuration | 29.6 KB | — |
| README.md | Documentation | 2.4 KB | — |
| adapter_chat_template.jinja | Other | 508 B | — |
| chat_template.jinja | Other | 508 B | — |
| colab_demo_vigyan_7b_quad_master.ipynb | Other | 6.3 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| adapter_tokenizer.json | Tokenizer | 7.1 MB | — |
| adapter_tokenizer_config.json | Tokenizer | 369 B | — |
| tokenizer.json | Tokenizer | 7.1 MB | — |
| tokenizer_config.json | Tokenizer | 369 B | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 19.1 GB
Released by Shreyansh singh through its official repository on Hugging Face. Read the license.
Built From
- Derived from allenai/OLMo-2-1124-7B-Instruct
- Quantized from allenai/OLMo-2-1124-7B-Instruct
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 19.1 GB |
| 16-bit | 14.6 GB |
| 8-bit | 7.3 GB |
| 4-bit | 3.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About vigyan-olmo2-7b-quad-master
How much GPU memory does vigyan-olmo2-7b-quad-master need?
About 17.5 GB at 16-bit and 4.4 GB at 4-bit: the weights (7.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run vigyan-olmo2-7b-quad-master on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use vigyan-olmo2-7b-quad-master commercially?
Not without separate permission. vigyan-olmo2-7b-quad-master is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
What is vigyan-olmo2-7b-quad-master's context length?
4,096 tokens, from the maximum position embeddings in its published configuration.