Autotrain compatible Avern Code Codegen Conversational Endpoints compatible General-intelligence Pytorch Qwen Qwen2 Qwen2.5 Reasoning Region:us Sharded Uk Unsloth
Model Card on HF 🤗: https://huggingface.co/averntech/KYRA-1.0X-Horizon
KYRA 1.0X Horizon Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
KYRA 1.0X Horizon Parameters and Internals
| LLM Name | KYRA 1.0X Horizon |
| Repository 🤗 | https://huggingface.co/averntech/KYRA-1.0X-Horizon |
| Model Name | Avern Prism 1.0X |
| Required VRAM | 29.7 GB |
| Updated | 2025-05-17 |
| Maintainer | averntech |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to KYRA 1.0X Horizon
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 | 128K / 15.2 GB | 50 | 0 |
| XJJ DeepSeek R1 COT | 128K / 0.1 GB | 6 | 0 |
| C3D4e5F6 | 128K / 1 GB | 630 | 0 |
| Qwerty2 05bita | 128K / 1 GB | 569 | 0 |
| B2C3D4e5 | 128K / 1 GB | 50 | 0 |
| RP Jp 2 | 32K / 1 GB | 7 | 1 |
| Qwen Coder7B Finetune | 32K / 15.2 GB | 7 | 0 |
| XFinder Qwen1505 | 32K / 0.9 GB | 5 | 4 |
| Quyen Mini V0.1 | 8K / 3.7 GB | 6 | 5 |
| Deep Ft12 Grp 16bit | 128K / 3.5 GB | 36 | 0 |
Rank the KYRA 1.0X Horizon Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 47402 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227