Llama 13B Benchmarks
ARC: 56.14-41.7%
HellaSwag: 80.92-15.1%
MMLU: 47.61-45%
TruthfulQA: 39.48-33.1%
WinoGrande: 76.24-12.9%
GSM8K: 7.58-91.8%
nn.n% — How the model compares to the GPT-4.
Llama 13B Parameters and Internals
| LLM Name | Llama 13B |
| Repository | Open on 🤗 |
| Model Size | 13b |
| Required VRAM | 26 GB |
| Updated | 2024-07-27 |
| Maintainer | huggyllama |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.28.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llama 13B
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Luminaura RP 13B | 0.2 | 128K / 26 GB | 7 | 0 |
| Yarn Llama 2 13B 128K | 0.2 | 128K / 26 GB | 57 | 113 |
| Agent Llama2 13B 80K | 0.2 | 80K / 26.4 GB | 7 | 0 |
| Chat Llama2 13B 80K | 0.2 | 80K / 52.8 GB | 8 | 0 |
| LongAlign 13B 64K | 0.2 | 64K / 26 GB | 96 | 12 |
| LongAlign 13B 64K Base | 0.2 | 64K / 26 GB | 11 | 3 |
| Openbuddy Llama2 13B V15p1 64K | 0.2 | 64K / 26.1 GB | 10 | 4 |
| Openbuddy Llama2 13b64k V15 | 0.2 | 64K / 26.1 GB | 11 | 1 |
| Yarn Llama 2 13B 64K | 0.2 | 64K / 26 GB | 32 | 18 |
| Airoboros L2 13B 2.1 YaRN 64K | 0.2 | 64K / 26 GB | 12 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than huggyllama/llama-13b .
Rank the Llama 13B 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501