--- base_model: - openai/gpt-oss-120b - MultiverseComputingCAI/HyperNova-60B library_name: transformers license: apache-2.0 ---
# HyperNova 60B 2605 ### Powered by CompactifAI [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![HuggingFace](https://img.shields.io/badge/🤗-Model_Hub-yellow.svg)](https://huggingface.co/MultiverseComputingCAI/HyperNova-60B-2605) [![Discord](https://img.shields.io/badge/Discord-Community-5865F2?logo=discord&logoColor=white)](https://discord.gg/cGas9uStqp) **Optimized for Efficient Inference** · **Reduced Memory Footprint** · **Native Tool Calling Support**
--- ## Table of Contents - [Highlights](#highlights) - [Model Overview](#model-overview) - [Key Characteristics](#key-characteristics) - [Quick Start](#quick-start) - [What's New in HyperNova 60B 2605](#whats-new-in-hypernova-60b-2605) - [Tool Calling](#tool-calling) - [Training & Fine-Tuning](#training--fine-tuning) - [Architecture](#architecture) - [Evaluation & Benchmarks](#evaluation--benchmarks) - [Languages](#languages) - [Intended Use](#intended-use) - [Safety & Limitations](#safety--limitations) - [Model Information](#model-information) - [Citation](#citation) --- ## Model Overview **HyperNova 60B 2605**, developed by **Multiverse Computing**, is an open-weight model designed for powerful **general** reasoning, **coding**, and versatile developer use. The model is **instruction-tuned** and supports **native tool calling** (function calling with defined schemas, structured outputs, and agent-style workflows). HyperNova 60B 2605 is intended for code generation, RAG, and tool-augmented applications. ## Technical Deep Dive For a detailed explanation of the compression architecture, model compression process, and benchmark results behind Hypernova-60B, read [this full technical article by Johanna Angulo, Evaluation Manager at Multiverse Computing.](https://multiversecomputing.com/papers/hypernova-60b-2602-same-intelligence-half-the-size-improved-tool-calling-capability) --- ## Key Characteristics | Characteristic | Description | |-----------------------|-------------| | 🛠️ **Tool calling** | Native support; OpenAI-style function / tool calling schemas; suited to coding agents and structured outputs | | 🧠 **Parameters** | 60B total parameters | | 📐 **Architecture** | Decoder-only Transformer | | Primary language | English | | Other languages | Not formally evaluated | --- ## Quick Start This model can be loaded with the **Transformers** API. Use `trust_remote_code=True` (required for the gpt-oss architecture). Recommended approach: `AutoModelForCausalLM` with `apply_chat_template`: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "MultiverseComputingCAI/HyperNova-60B-2605" tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( model_id, device_map="auto", torch_dtype="auto", trust_remote_code=True, ) messages = [{"role": "user", "content": "What is a Hypernova?"}] inputs = tokenizer.apply_chat_template( messages, return_tensors="pt", add_generation_prompt=True, ) inputs = inputs.to(model.device) attention_mask = torch.ones_like(inputs, dtype=torch.long, device=inputs.device) outputs = model.generate( inputs, max_new_tokens=512, do_sample=True, temperature=0.7, attention_mask=attention_mask, ) reply = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True) print(reply) ``` Alternatively you can use the `pipeline` API with `trust_remote_code=True`; the pipeline returns the full conversation structure, so extract the assistant message from `outputs[0]["generated_text"]` as needed. --- ## What’s New in HyperNova 60B 2605 **HyperNova 60B 2605** is an improved version of **HyperNova 60B 2602**, with this release focused on **coding** and **general** capability backed by higher scores on several benchmarks. ### Summary - **Improvement focus vs HyperNova 60B 2602:** stronger **coding** (coding-style tasks) and **general** benchmark performance. - **Tool use:** Retains native support for function calling, structured outputs, and agent-style workflows (OpenAI-style schemas). - **Reasoning:** Compatible with configurable reasoning effort (e.g. low / medium / high in system prompt) where the format is preserved; full chain-of-thought available for debugging and analysis. - **Evaluated** on coding and tool-heavy benchmarks (e.g. Tau2-bench, Terminal-Bench) alongside **general** intelligence benchmarks. --- ## Tool Calling HyperNova 60B 2605 supports **native tool use** and is well-suited for: - **Function calling** with defined schemas - **Structured outputs** - **Coding-oriented tool workflows** (e.g. browser tasks, code execution where supported) The model can detect when to invoke tools, emit structured JSON tool calls, and consume tool outputs to continue generation. Tool-calling behavior follows **OpenAI-style schemas**; compatibility refers to format and structure—exact parity with the base or other models is not guaranteed. Compared with HyperNova 60B 2602, this release improves on **coding** and **general** evaluation tracks—including IFBench, Tau2-bench, Terminal Bench, and AA-LCR under the high-reasoning setup reported below. ### Example Tool Call ```json { "name": "get_weather", "arguments": { "city": "Paris", "date": "2026-02-10" } } ``` --- ## Architecture ### Model Specifications | Specification | Value | |-------------------|--------------------| | Total parameters | 60B, 4.8B active MoE | --- ## Evaluation & Benchmarks ### Evaluation Methodology Benchmark scores were obtained with the following setups. Methodology varies by benchmark family. #### HLE, MMLU-Pro, AIME25, GPQA:d, LiveCodeBench - **Evaluation framework**: [Nemo-skills](https://github.com/NVIDIA/NeMo-Skills) - **Inference library**: vLLM 0.13.0 - **Hardware**: 1× NVIDIA H200 Tensor Core GPU - **Reasoning effort**: high - **Decoding**: temperature = 1.0, top_p = 1.0 - **Batch size**: 64 #### IFBench, AA-LCR, SciCode - **Evaluation framework**: [Nemo-skills](https://github.com/NVIDIA/NeMo-Skills) - **Inference library**: vLLM 0.13.0 - **Hardware**: 1× NVIDIA H200 Tensor Core GPU - **Reasoning effort**: high - **Decoding**: temperature = 1.0,top_p = 1.0 - **Batch size**: 64 #### Tau2-bench (Telecom) - **Evaluation framework**: [EvalScope](https://github.com/EvalScope/EvalScope) 1.4.1 - **Inference library**: vLLM 0.13.0 - **Hardware**: 1× NVIDIA H200 Tensor Core GPU - **Reasoning effort**: high (agent `extra_body.reasoning_effort`) - **Decoding (agent)**: temperature = 1.0, top_p = 1.0, min_tokens = 1 - **Decoding (judge / user simulator)**: temperature = 0.7, timeout = 600 - **Reproducibility**: subset telecom (default); max steps 100; repeats 3; tool-call parser openai (agent), hermes (judge) #### Terminal-Bench Hard (Artificial Analysis subset): - **Evaluation framework**: laude-institute/harbor == 0.1.43 - **Inference library**: vLLM == 0.13.0 - **Hardware**: 1× NVIDIA H200 Tensor Core GPU - **Reasoning effort**: high - **Decoding**: temperature = 1.0, top_p = 1.0, max-model-len = 131072 - **Reproducibility**: subset from AA (https://artificialanalysis.ai/methodology/intelligence-benchmarking#terminal-bench-hard) - **Agent**: terminus-2, max episodes 100; repeats 3; #### Aider polyglot - **Evaluation framework**: [Aider-AI/aider](https://github.com/Aider-AI/aider) - **Hardware**: 2× NVIDIA H200 Tensor Core GPU (host with Docker) - **Dataset**: `polyglot-benchmark` (225 exercises across multiple languages) - **Reasoning effort**: high (passed via `--reasoning-effort`) - **Decoding**: temperature = 1.0, top_p = 1.0 (configurable via `generation_config` / `--read-model-settings` YAML) - **Edit format**: `whole` (also supports `diff | udiff | diff-fenced | architect`) - **Reproducibility**: leaderboard-aligned; `--tries=2` (repeats) ### Quantitative Results (Reported & Planned) | Benchmark | gpt-oss-120b | HyperNova 60B 2602 | HyperNova 60B 2605 | |-----------------------|-------------------------------|-----------------------------|--------------------------| | HLE | 18.50 | 7.28 | 14.97 | | MMLU-Pro | 79.64 | 74.25 | 76.77 | | Tau2-bench (Telecom) | 63.74 | 60.53 | 61.70 | | AIME25 | 93.67 | 86.00 | 90.00 | | GPQA:d | 74.64 | 65.56 | 71.92 | | IFBench | 67.01 | 59.40 | 66.57 | | SciCode | 41.52 | 33.53 | 36.00 | | LiveCodeBench | 62.75 | 51.53 | 68.68 | | Terminal Bench | 24.24 | 12.12 | 15.91 | | AA-LCR | 49.00 | 35.67 | 40.33 | | AIDER | 43.60 | 26.2 | 34.2 | ![Benchmarks](assets/benchmarks.png) ![LiveCodeBench](assets/livecodebench.png) ### Quantitative Results (Inference Performance) #### Metrics reported - **System Output Throughput (higher is better)**: Mean output tokens per second across all concurrent requests over the benchmarking phase. - **End-to-End Latency per Query (lower is better):** Median end-to-end response time for each query from the time the query is sent. - **Output Speed per Query (higher is better):** Median output tokens per second after the first token is received for each query. - **Time to first token (TTFT) (lower is better):** Median time to first token. - **Estimated total memory — (lower is better):** Median from each GuideLLM phase (estimated total footprint: weights plus KV contribution from monitored usage). - **Model weights (lower is better):** On the same hardware and harness, **HyperNova 60B 2605** is compared to **gpt-oss-120b** using GuideLLM. Each table lists **median** values for that model at each **concurrency phase** (1 → 256 concurrent requests). | Metric | GPT-OSS-120B | Hypernova 60B 2605 | |--------|-------------:|-------------------:| | Concurrency | 128 | 128 | | Throughput (tok/s) | 3,821 | 5,210 | | E2E latency (s) | 24.05 | 14.74 | | Output speed (tok/s) | 57.79 | 69.31 | | TTFT (s) | 7.04 | 4.85 | | Est. total memory (GB) | 123.55 | 38.83 | | Model weights (GB) | 121.54 | 31.81 | #### Performance evaluation conditions Our performance evaluation follows the spirit of [Artificial Analysis](https://artificialanalysis.ai/methodology/system-load-test). - **Inference library**: vLLM 0.13.0 - **Monitoring libraries**: GuideLLM, nvidia-ml-py - **Hardware**: 1× NVIDIA H200 Tensor Core GPU - **Conditions**: **concurrency phases** 1, 2, 4, 8, 16, 32, 64, 128, 192, and 256 concurrent requests (one GuideLLM phase each) - **Phase duration**: Each phase lasts 3 minutes (excluding ramp-up and cool-down periods). - **Workload shape:** input length is ~1000 tokens per query (median); median output length varies by phase and model. - **Streaming**: Benchmarking is conducted with streaming enabled. The figure below is a **side-by-side comparison at concurrency = 128 only** ![Performance](assets/performance.png) --- ## Languages - **Primary language**: English - **Other languages**: Not formally evaluated The model was trained primarily on English-language data. Performance on other languages may vary and has not been systematically measured. --- ## Intended Use ### Recommended Use Cases - **Reasoning and analysis** (with configurable reasoning effort where supported) - **Tool-augmented applications**, with emphasis on **coding** and **general** assistant use (function calling, web browsing, code execution, structured outputs) - **Code generation and reasoning** - **Chatbots and virtual assistants** - **Retrieval-augmented generation (RAG)** ### Out-of-Scope Uses - Harmful, illegal, or deceptive content generation - Impersonation of real individuals without consent - High-risk decision-making without human oversight - Surveillance or tracking of individuals - Any use that violates applicable laws or regulations --- ## Safety & Limitations ### Known Limitations - **English-centric** training data. - **Format:** For best results, use the same [harmony response format](https://huggingface.co/openai/gpt-oss-120b) as gpt-oss-120b where applicable; behavior may differ otherwise. - **Tool calling** depends on correct schema and tool design; exact parity with gpt-oss-120b or other models is not guaranteed. ### Recommendations - Validate tool outputs before execution - Use human oversight for critical applications - Perform task-specific evaluation prior to deployment --- ## Model Information | Field | Value | |--------------|--------------------- | | Model name | HyperNova 60B 2605 | | Version | 2605 | | Release date | 26/02/2026 | | Developed by | Multiverse Computing | | License | Apache 2.0 | | Contact | business@multiversecomputing.com | --- ## Citation If you use this model, please cite the base model and this variant: ```bibtex @misc{openai2025gptoss120b, title = {gpt-oss-120b \& gpt-oss-20b Model Card}, author = {OpenAI}, year = {2025}, eprint = {2508.10925}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, url = {https://arxiv.org/abs/2508.10925} } @misc{hypernova60b2605, title = {HyperNova 60B 2605: Model developed based on gpt-oss-120b}, author = {Multiverse Computing}, year = {2026}, url = {https://huggingface.co/MultiverseComputingCAI/HyperNova-60B-2605}, note = {Model developed based on openai/gpt-oss-120b using CompactifAI technology} } ``` **Built by [Multiverse Computing](https://www.multiversecomputing.com)** · [Report an issue](https://huggingface.co/MultiverseComputingCAI/HyperNova-60B-2605/discussions) · [Discord](https://discord.gg/8mT9FveN)