Merged Model Autotrain compatible Base model:claudioitaly/underg... Base model:finetune:claudioita... Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheHierophant/Underground-Cognitive-V0.3-test
Underground Cognitive V0.3 Test Benchmarks
MMLU Pro: 25.75
GPQA: 6.49
MUSR: 14.56
BBH: 33.67
IFEval: 48.08 vs 88 (so35)-45.4%
MATH Lvl 5: 0.6
LLME Score: 0.33049
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)
Underground Cognitive V0.3 Test Parameters and Internals
| LLM Name | Underground Cognitive V0.3 Test |
| Repository 🤗 | https://huggingface.co/TheHierophant/Underground-Cognitive-V0.3-test |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 10.7b |
| Required VRAM | 21.4 GB |
| Updated | 2024-12-21 |
| Maintainer | TheHierophant |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Underground Cognitive V0.3 Test
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SOLAR 10.7B Instruct V1.0 128K | 128K / 21.4 GB | 152 | 4 |
| SOLAR 10.7B V1.0 Instruct 16K | 16K / 21.4 GB | 63 | 2 |
| SOLAR 10.7B V1.0 Base 16K | 16K / 21.4 GB | 69 | 0 |
| SauerkrautLM SOLAR Instruct | 8K / 21.4 GB | 808 | 46 |
| MetaModelv2 | 8K / 21.4 GB | 1174 | 0 |
| PiVoT SOLAR 10.7B RP | 8K / 21.4 GB | 755 | 7 |
| Fimbulvetr V2 Kuro Lotus Bf16 | 8K / 21.5 GB | 36 | 3 |
| Kazemi 1.2 Solar | 8K / 21.4 GB | 0 | 0 |
| Bucharest 0.2 | 5K / 21.4 GB | 36 | 1 |
| SOLAR 10.7B Instruct V1.0 | 4K / 21.4 GB | 62998 | 619 |
Note: green Score (e.g. "73.2") means that the model is better than TheHierophant/Underground-Cognitive-V0.3-test .
Rank the Underground Cognitive V0.3 Test 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? 40013 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217