4-bit 4bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Model-index Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
RYS Huge Bnb 4bit Benchmarks
MMLU Pro: 48.8
GPQA: 17.9
MUSR: 22.84
BBH: 57.53
IFEval: 59.68 vs 88 (so35)-32.2%
MATH Lvl 5: 31.57
LLME Score: 0.36732
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)
RYS Huge Bnb 4bit Parameters and Internals
| LLM Name | RYS Huge Bnb 4bit |
| Repository 🤗 | https://huggingface.co/dnhkng/RYS-Huge-bnb-4bit |
| Model Size | 55b |
| Required VRAM | 57.2 GB |
| Updated | 2024-08-06 |
| Maintainer | dnhkng |
| Model Type | qwen2 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the RYS Huge Bnb 4bit 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? 37405 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803