Arxiv:2311.03099 Autotrain compatible Endpoints compatible Merge Mergekit Mistral Region:us Safetensors Sharded Tensorflow
Supermario V4 Benchmarks
ARC: 73.46-23.7%
HellaSwag: 88.77-6.9%
MMLU: 65.41-24.4%
TruthfulQA: 72.0722.2%
WinoGrande: 85.24-2.6%
GSM8K: 70.13-23.8%
nn.n% — How the model compares to the GPT-4.
Supermario V4 Parameters and Internals
| LLM Name | Supermario V4 |
| Repository | Open on 🤗 |
| Model Size | 7.2b |
| Required VRAM | 14.4 GB |
| Updated | 2024-07-26 |
| Maintainer | vanillaOVO |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Supermario V4
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Openchat 3.5 0106 128K DPO | 0.2 | 128K / 14.4 GB | 309 | 2 |
| Instruction Synthesizer | 0.3 | 32K / 28.9 GB | 1046 | 55 |
| Mistral RAG | 0.3 | 32K / 14.4 GB | 13255 | 11 |
| Cymist2 V01 SFT | 0.3 | 32K / 14.4 GB | 2083 | 1 |
| CatunaMayo DPO | 0.3 | 32K / 14.4 GB | 327 | 0 |
| CatunaMayo | 0.3 | 32K / 14.4 GB | 313 | 0 |
| Maestrale Chat V0.4 Beta | 0.3 | 32K / 14.4 GB | 1977 | 2 |
| ... Alpha Instruction Tuned SLERP | 0.3 | 32K / 14.5 GB | 1865 | 0 |
| ...stral 1 From Mixtral 8x7B V0.1 | 0.3 | 32K / 14.4 GB | 276 | 1 |
| Zion Alpha Instruction Tuned | 0.3 | 32K / 14.5 GB | 1910 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than vanillaOVO/supermario_v4 .
Rank the Supermario V4 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501