Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Instruct Mixtral Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/VictorDCh/Llama-3-8B-Instruct-MoE-2
Llama 3 8B Instruct MoE 2 Benchmarks
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)
Llama 3 8B Instruct MoE 2 Parameters and Internals
| LLM Name | Llama 3 8B Instruct MoE 2 |
| Repository 🤗 | https://huggingface.co/VictorDCh/Llama-3-8B-Instruct-MoE-2 |
| Model Size | 24.9b |
| Required VRAM | 50 GB |
| Updated | 2024-12-22 |
| Maintainer | VictorDCh |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3 8B Instruct MoE 2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| L3.1 MoE 4x8B V0.2 | 128K / 50.1 GB | 35 | 2 |
| OpenCrystal V4 L3 4x8B | 8K / 50 GB | 9 | 2 |
| ...ama 3 Aplite Instruct 4x8B MoE | 8K / 50 GB | 462 | 38 |
| L3 Arcania 4x8b | 8K / 50 GB | 402 | 22 |
| Llama 3 4x8B | 8K / 49.9 GB | 13 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than VictorDCh/Llama-3-8B-Instruct-MoE-2 .
Rank the Llama 3 8B Instruct MoE 2 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217