Arxiv:2406.16554 Autotrain compatible Custom code En Llama moe Moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/llama-moe/LLaMA-MoE-v1-3_5B-4_16-sft
LLaMA MoE V1 3 5B 4 16 Sft 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 MoE V1 3 5B 4 16 Sft Parameters and Internals
| Model Type |
| |||||||||
| Supported Languages |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | LLaMA MoE V1 3 5B 4 16 Sft |
| Repository 🤗 | https://huggingface.co/llama-moe/LLaMA-MoE-v1-3_5B-4_16-sft |
| Model Size | 6.7b |
| Required VRAM | 13.5 GB |
| Updated | 2025-09-23 |
| Maintainer | llama-moe |
| Model Type | llama_moe |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaMoEForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to LLaMA MoE V1 3 5B 4 16 Sft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| LLaMA MoE V1 3 5B 2 8 Sft | 4K / 13.5 GB | 9 | 3 |
| LLaMA MoE V1 3 0B 2 16 Sft | 4K / 13.5 GB | 5 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than llama-moe/LLaMA-MoE-v1-3_5B-4_16-sft .
Rank the LLaMA MoE V1 3 5B 4 16 Sft 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124