Arxiv:2203.05482 Autotrain compatible Base model:merge:vicgalle/carb... Base model:merge:vicgalle/role... Base model:vicgalle/carbonbeag... Base model:vicgalle/rolebeagle... Conversational Endpoints compatible Merge Mergekit Mistral Region:us Safetensors Sharded Tensorflow
Test1 Benchmarks
ARC: 72.27 vs 96.7 (so35)-25.3%
HellaSwag: 89.52 vs 95.3 (gpt4)-6.1%
MMLU: 66.67 vs 88.3 (so35)-24.5%
TruthfulQA: 78.32 vs 59 (gpt4)32.7%
WinoGrande: 83.9 vs 87.5 (gpt4)-4.1%
GSM8K: 64.67 vs 96.4 (so35)-32.9%
LLME Score: 0.19663
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)
Test1 Parameters and Internals
| LLM Name | Test1 |
| Repository 🤗 | https://huggingface.co/vicgalleorg/test1 |
| Base Model(s) | |
| Model Size | 11b |
| Required VRAM | 21.4 GB |
| Updated | 2024-10-22 |
| Maintainer | vicgalleorg |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Test1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Starling LM 11B Alpha | 32K / 21.4 GB | 1254 | 12 |
| CarbonBeagle 11B Truthy | 32K / 21.4 GB | 11742 | 9 |
| ConfigurableBeagle 11B | 32K / 21.4 GB | 4269 | 2 |
| CarbonBeagle 11B | 32K / 21.4 GB | 6418 | 9 |
| Alphacode MALI 11B Slowtest | 32K / 21.8 GB | 1914 | 0 |
| Alphacode MALI 11B | 32K / 21.8 GB | 1882 | 1 |
| Mistral 11B Miniplatypus | 32K / 21.5 GB | 5 | 0 |
| Mistral Evolved 11B V0.1 | 32K / 22.3 GB | 58 | 33 |
| Elysium Omni Itt 11B | 32K / 22.3 GB | 6 | 0 |
| Elysium2 11B | 32K / 22.3 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than vicgalleorg/test1 .
Rank the Test1 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? 37106 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803