Arxiv:1902.00751 Arxiv:2212.05055 Arxiv:2305.14314 Arxiv:2401.02731 Autotrain compatible Camelidae Custom code Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:meta-math/metamathqa Dataset:open-orca/slimorca En Endpoints compatible Instruct Moe Pytorch Region:us Sharded
Camelidae 8x7B Benchmarks
ARC: 55.63 vs 96.7 (so35)-42.5%
HellaSwag: 79.18 vs 95.3 (gpt4)-16.9%
MMLU: 50.1 vs 88.3 (so35)-43.3%
TruthfulQA: 42.86 vs 59 (gpt4)-27.4%
WinoGrande: 76.24 vs 87.5 (gpt4)-12.9%
GSM8K: 22.82 vs 96.4 (so35)-76.3%
LLME Score: 0.22569
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)
Camelidae 8x7B Parameters and Internals
| LLM Name | Camelidae 8x7B |
| Repository 🤗 | https://huggingface.co/hywu/Camelidae-8x7B |
| Required VRAM | 15.6 GB |
| Updated | 2024-10-07 |
| Maintainer | hywu |
| Model Type | camelidae |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | modeling_camelidae.LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Camelidae 8x7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Camelidae 8x13B | 4K / 29.4 GB | 1178 | 4 |
| Camelidae 8x34B | 4K / 76 GB | 1170 | 28 |
Rank the Camelidae 8x7B 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? 36599 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803