Upload 4 files

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/intelligence.png filter=lfs diff=lfs merge=lfs -text
+assets/performance.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,336 @@
----
-license: apache-2.0
----
+---
+base_model:
+- openai/gpt-oss-120b
+- MultiverseComputingCAI/HyperNova-60B
+library_name: transformers
+---
+<div align="center">
+
+# HyperNova 60B 2602
+
+### 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-2602)
+[![Discord](https://img.shields.io/badge/Discord-Community-5865F2?logo=discord&logoColor=white)](https://discord.gg/8mT9FveN)
+
+**Optimized for Efficient Inference** · **Reduced Memory Footprint** · **Native Tool Calling Support**
+
+</div>
+
+---
+
+## Table of Contents
+
+- [Highlights](#highlights)
+- [Model Overview](#model-overview)
+- [Key Characteristics](#key-characteristics)
+- [Quick Start](#quick-start)
+- [What's New in HyperNova 60B 2602](#whats-new-in-hypernova-60b-2602)
+- [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 2602** is a **model developed based on [OpenAI’s gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)**, developed by **Multiverse Computing**. The original gpt-oss-120b is an open-weight model (117B parameters, 5.1B active in MoE) designed for powerful reasoning, agentic tasks, and versatile developer use. This version is compressed with **CompactifAI**, Multiverse Computing’s proprietary technology, reducing parameter count and memory requirements while aiming to preserve strong reasoning, tool-use, and (where applicable) compatibility with the [harmony response format](https://huggingface.co/openai/gpt-oss-120b) and tool-calling behavior of the base model.
+
+The model is **instruction-tuned** and supports **native tool calling** (function calling with defined schemas, structured outputs, and agent-style workflows). HyperNova 60B 2602 is intended for the same broad use cases as gpt-oss-120b—reasoning, code generation, RAG, and tool-augmented applications—with **lower memory footprint** and deployment flexibility.
+
+---
+
+## Key Characteristics
+
+| Characteristic        | Description |
+|-----------------------|-------------|
+| Base model            | [OpenAI gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) (117B params, MoE; open-weight, Apache 2.0) |
+| 🛠️ **Tool calling**  | Native support; OpenAI-style function / tool calling schemas; agentic use (e.g. function calling, structured outputs) |
+| 🧠 **Parameters**     | 60B total parameters after CompactifAI compression (reduced vs. base 117B) |
+| 📐 **Architecture**   | Decoder-only Transformer (from gpt-oss lineage) |
+| 🗜️ **Compression**   | CompactifAI (proprietary compression technology) |
+| 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-2602"
+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 2602
+
+**HyperNova 60B 2602** is a model developed based on **gpt-oss-120b**, retaining the base model’s strengths while reducing memory and improving deployment flexibility.
+
+### Summary
+
+- **Model developed based on [gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b):** Same Apache 2.0 license and design goals (reasoning, agentic tasks, tool use); smaller footprint via CompactifAI.
+- **Tool use:** Retains 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 tool-focused benchmarks (e.g. BFCL v4, Tau2-bench) and general benchmarks alongside other CompactifAI and gpt-oss variants.
+
+---
+
+## Tool Calling
+
+As with the base [gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) model, HyperNova 60B 2602 supports **native tool use** and is well-suited for:
+
+- **Function calling** with defined schemas  
+- **Structured outputs**  
+- **Agentic operations** (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.
+
+### Example Tool Call
+
+```json
+{
+  "name": "get_weather",
+  "arguments": {
+    "city": "Paris",
+    "date": "2026-02-10"
+  }
+}
+```
+
+---
+
+## Training & Fine-Tuning
+
+### Base Model: gpt-oss-120b
+
+The base model [gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) was trained on OpenAI’s **harmony response format** and is intended for use with that format for correct behavior. It supports configurable reasoning levels (low / medium / high) and native tool use. See the [original model card](https://huggingface.co/openai/gpt-oss-120b) and [arXiv:2508.10925](https://arxiv.org/abs/2508.10925) for details.
+
+### CompactifAI Compression & Optional Fine-Tuning
+
+- **Compression:** CompactifAI was applied to produce a smaller, efficient model (60B parameters) while aiming to preserve reasoning and tool-use capabilities.
+- **Optional fine-tuning:** This variant may include additional fine-tuning for tool calling and structured outputs; exact training details are model-specific.
+
+---
+
+## Architecture
+
+### Model Specifications
+
+| Specification     | Value              |
+|-------------------|--------------------|
+| Base model        | [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) (117B params, 5.1B active MoE) |
+| Total parameters  | 60B, 4.8B active MoE |
+
+---
+
+## Evaluation & Benchmarks
+
+### Evaluation Methodology
+
+Benchmark scores were obtained with the following setups. Methodology varies by benchmark family.
+
+#### MMLU-Pro, AIME25, GPQA:d, LiveCodeBench
+
+- **Evaluation framework**: [Lighteval](https://github.com/huggingface/lighteval) 
+- **Inference library**: vLLM 0.14.0  
+- **Reasoning effort**: medium  
+- **Decoding**: temperature = 0.6, max_tokens = 131072, top_p = 1.0, top_k = 0  
+- **Batch size**: 64  
+
+#### IFBench, AA-LCR, SciCode
+
+- **Evaluation framework**: [Nemo-skills](https://github.com/NVIDIA/NeMo-Skills) 
+- **Inference library**: vLLM 0.14.0  
+- **Reasoning effort**: medium  
+- **Decoding**: temperature = 1.0, max_tokens = 131072, top_p = 1.0, top_k = 0  
+- **Batch size**: 64
+  
+#### BFCL v4 (17 splits)
+
+- **Evaluation framework**: [EvalScope](https://github.com/EvalScope/EvalScope) 1.4.1
+- **Inference library**: vLLM 0.14.0  
+- **Reasoning effort**: high  
+- **Decoding**: temperature = 0.6, max_tokens = 16384, parallel_tool_calls = true, tool-call parser openai
+
+#### Tau2-bench (Telecom)
+
+- **Evaluation framework**: [EvalScope](https://github.com/EvalScope/EvalScope) 1.4.1
+- **Inference library**: vLLM 0.14.0  
+- **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 == 0.15.0
+- **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;
+
+### Quantitative Results (Reported & Planned)
+
+Scores are accuracy or benchmark-specific metrics. Use `—` or *TBD* for evaluations not yet run. Reported numbers use the methodology described above (reasoning: cai-eval + Nemo-skills; BFCL v4 and Tau2-bench: cai-eval + EvalScope); other entries to be documented.
+
+| Benchmark             | gpt-oss-20b           | gpt-oss-120b           | HyperNova 60B 2602       |
+|-----------------------|-----------------------|------------------------|--------------------------|
+| MMLU-Pro              | 74                    | 78                     | 74                       |
+| BFCL v4               | 61                    | 64                     | 62                       |
+| Tau2-bench (Telecom)  | 59                    | 68                     | 61                       |
+| AIME25                | 72                    | 80                     | 76                       |
+| GPQA:d                | 63                    | 69                     | 69                       |
+| IFBench               | 55                    | 63                     | 60                       |
+| SciCode               | 34                    | 38                     | 32                       |
+| LiveCodeBench         | 64                    | 66                     | 64                       |
+| Terminal Bench        | 9                     | 22                     | 16                       |
+| AA-LCR                | 37                    | 50                     | 36                       |
+| AA-Omnis. Index       | -40                   | -36                    | -41                      |
+| AA-Omnis. Accuracy    | 16                    | 21                     | 15                       |
+
+![Intelligence](assets/intelligence.png)
+![Tool-calling](assets/tool-calling.png)
+
+### Quantitative Results (Inference Performance)
+
+Representative throughput and memory under the evaluation setup above. Comparison against **gpt-oss-20b** and **gpt-oss-120b** on the same hardware.
+
+#### Performance evaluation conditions
+
+Describe the setup used to obtain the numbers in the table below (replace the placeholders or add a short paragraph):
+
+- **Inference library**: vLLM 0.14.0
+- **Hardware**: 4× NVIDIA H200 Tensor Core GPU
+- **Conditions**: batch size=512, context length=512, decode length=256
+- **Notes**: dtype=default
+
+| Metric                     | gpt-oss-20b              | gpt-oss-120b             | HyperNova 60B 2602       | Hardware                      |
+|----------------------------|--------------------------|--------------------------|--------------------------|-------------------------------|
+| Tokens / second (decode)   | 250                      | 228                      | 240                      | 4× NVIDIA H200 Tensor Core GPU|
+| Time to first token (ms)   | 26                       | 26                       | 25                       | 4× NVIDIA H200 Tensor Core GPU|
+| Peak GPU memory (GB)       | 13                       | 61                       | 32                       | 4× NVIDIA H200 Tensor Core GPU|
+
+![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
+
+Aligned with [gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) use cases, with the benefit of a smaller footprint:
+
+- **Reasoning and analysis** (with configurable reasoning effort where supported)  
+- **Tool-augmented and agentic applications** (function calling, web browsing, code execution, structured outputs)  
+- **Code generation and reasoning**  
+- **Chatbots and virtual assistants**  
+- **Retrieval-augmented generation (RAG)**  
+- **Deployments** where gpt-oss-120b is desirable but memory or latency is constrained  
+
+### 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 (inherited from base model).  
+- **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.  
+- **Compression** may affect some behaviors; evaluate for your use case.  
+
+### 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 2602   |
+| Based on     | [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) |
+| Version      | 2602                 |
+| 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{hypernova60b2602,
+  title = {HyperNova 60B 2602: Model developed based on gpt-oss-120b},
+  author = {Multiverse Computing},
+  year = {2026},
+  url = {https://huggingface.co/MultiverseComputingCAI/HyperNova-60B-2602},
+  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-2602/discussions) · [Discord](https://discord.gg/8mT9FveN)