Merged Model 4-bit Autotrain compatible Bitsandbytes En Endpoints compatible Llama Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/vihangd/smart-dan-sft-v0.1
Smart Dan Sft V0.1 Benchmarks
MMLU Pro: 1.58
GPQA: 0.67
MUSR: 1.11
BBH: 3.13
IFEval: 15.76 vs 88 (so35)-82.1%
MATH Lvl 5: 0.45
LLME Score: 0.22006
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)
Smart Dan Sft V0.1 Parameters and Internals
| Supported Languages |
|
| LLM Name | Smart Dan Sft V0.1 |
| Repository 🤗 | https://huggingface.co/vihangd/smart-dan-sft-v0.1 |
| Merged Model | Yes |
| Model Size | 379.5m |
| Required VRAM | 0.7 GB |
| Updated | 2025-01-24 |
| Maintainer | vihangd |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.42.4 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 32001 |
| Torch Data Type | float32 |
Rank the Smart Dan Sft V0.1 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? 41817 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227