Base model:jacoby746/proto-har... Base model:jacoby746/proto-har... Base model:jacoby746/proto-har... Base model:merge:jacoby746/pro... Base model:merge:jacoby746/pro... Base model:merge:jacoby746/pro... Merge Mergekit Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B
Proto Harpy Blazing Light V0.1 2x7B Benchmarks
MMLU Pro: 25.57
GPQA: 6.04
MUSR: 14.12
BBH: 32.63
IFEval: 49.05 vs 88 (so35)-44.3%
MATH Lvl 5: 7.48
LLME Score: 0.27959
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)
Proto Harpy Blazing Light V0.1 2x7B Parameters and Internals
| LLM Name | Proto Harpy Blazing Light V0.1 2x7B |
| Repository 🤗 | https://huggingface.co/Jacoby746/Proto-Harpy-Blazing-Light-v0.1-2x7B |
| Base Model(s) | |
| Model Size | 12.9b |
| Required VRAM | 25.8 GB |
| Updated | 2025-02-22 |
| Maintainer | Jacoby746 |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Proto Harpy Blazing Light V0.1 2x7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MixTAO 7Bx2 MoE V8.1 | 32K / 25.8 GB | 9578 | 55 |
| Inf Silent Kunoichi V0.1 2x7B | 32K / 25.6 GB | 5 | 0 |
| Inf Silent Kunoichi V0.2 2x7B | 32K / 25.6 GB | 8 | 0 |
| MixTAO 7Bx2 MoE V8.1 | 32K / 25.8 GB | 8760 | 52 |
| MultiMash8 13B Slerp | 32K / 25.7 GB | 6 | 0 |
| MultiMash11 13B Slerp | 32K / 25.7 GB | 6 | 0 |
| MultiMash9 13B Slerp | 32K / 25.7 GB | 8 | 0 |
| MultiMash10 13B Slerp | 32K / 25.7 GB | 12 | 0 |
| Mixtral 7Bx2 MoE | 32K / 25.8 GB | 1832 | 36 |
| MixTaoTruthful 13B Slerp | 32K / 25.7 GB | 8 | 0 |
Rank the Proto Harpy Blazing Light V0.1 2x7B 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227