Ai assistant Autotrain compatible Cipher Code generation Codegen Conversational En Endpoints compatible Helpingai Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/HelpingAI/Cipher-20B
Cipher 20B Benchmarks
MMLU Pro: 30.49
GPQA: 6.04
MUSR: 8.17
BBH: 43.44
IFEval: 53.78 vs 88 (so35)-38.9%
MATH Lvl 5: 19.94
LLME Score: 0.26896
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)
Cipher 20B Parameters and Internals
| LLM Name | Cipher 20B |
| Repository 🤗 | https://huggingface.co/HelpingAI/Cipher-20B |
| Model Size | 20b |
| Required VRAM | 41.4 GB |
| Updated | 2025-09-23 |
| Maintainer | HelpingAI |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Cipher 20B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Sailor2 20B Chat | 4K / 38.6 GB | 1090 | 7 |
Rank the Cipher 20B 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124