Allenai/tulu-2-dpo-7b Autotrain compatible Endpoints compatible Merge Mixtral Moe Region:us Safetensors Sharded Technoculture/mt7bi-dpo Tensorflow
Model Card on HF 🤗: https://huggingface.co/Technoculture/Medtulu-2x7b
Medtulu 2x7b Benchmarks
ARC: 54.61 vs 96.7 (so35)-43.5%
HellaSwag: 75.68 vs 95.3 (gpt4)-20.6%
MMLU: 49.12 vs 88.3 (so35)-44.4%
TruthfulQA: 50.04 vs 59 (gpt4)-15.2%
WinoGrande: 72.85 vs 87.5 (gpt4)-16.7%
GSM8K: 16.98 vs 96.4 (so35)-82.4%
LLME Score: 0.1751
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)
Medtulu 2x7b Parameters and Internals
| Model Type |
|
| LLM Name | Medtulu 2x7b |
| Repository 🤗 | https://huggingface.co/Technoculture/Medtulu-2x7b |
| Model Size | 11.1b |
| Required VRAM | 22.1 GB |
| Updated | 2025-09-20 |
| Maintainer | Technoculture |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32017 |
| Torch Data Type | bfloat16 |
Best Alternatives to Medtulu 2x7b
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| DevPearl 2x7B | 16K / 22.3 GB | 5 | 2 |
| Medorca 2x7b | 4K / 35.6 GB | 1650 | 2 |
| Phi3 4x4b Uninitialized | 4K / 22.2 GB | 5 | 0 |
| Medchator 2x7b | 4K / 22.1 GB | 6 | 1 |
| Youri 2x7b Dev | 4K / 22.1 GB | 5 | 4 |
| Youri 2x7b V0.2 | 4K / 22.1 GB | 5 | 1 |
Rank the Medtulu 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? 51483 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124