Autotrain compatible Axolotl Base model:allenai/olmoe-1b-7b... Base model:finetune:allenai/ol... Conversational Endpoints compatible Moe Olmoe Region:us Roleplay Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/allura-org/MoE-Girl-1BA-7BT
MoE Girl 1BA 7BT Benchmarks
MMLU Pro: 2.42
GPQA: 1.12
MUSR: 1.48
BBH: 4.84
IFEval: 27.05 vs 88 (so35)-69.3%
MATH Lvl 5: 1.51
LLME Score: 0.24207
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)
MoE Girl 1BA 7BT Parameters and Internals
| LLM Name | MoE Girl 1BA 7BT |
| Repository 🤗 | https://huggingface.co/allura-org/MoE-Girl-1BA-7BT |
| Base Model(s) | |
| Model Size | 6.9b |
| Required VRAM | 13.8 GB |
| Updated | 2025-02-22 |
| Maintainer | allura-org |
| Model Type | olmoe |
| Model Files | |
| Model Architecture | OlmoeForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.45.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 50304 |
| Torch Data Type | bfloat16 |
Rank the MoE Girl 1BA 7BT 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