Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Codefuse-ai/codefuse-deepseek-... Codegen Conversational Deepseek-ai/deepseek-coder-33b... Endpoints compatible Instruct Lazymergekit Llama Merge Mergekit Region:us Safetensors Sharded Tensorflow Wizardlm/wizardcoder-33b-v1.1
ValidateAI 3 33B Ties Benchmarks
ARC: 45.99 vs 96.7 (so35)-52.4%
HellaSwag: 61.71 vs 95.3 (gpt4)-35.2%
MMLU: 44.04 vs 88.3 (so35)-50.1%
TruthfulQA: 42.26 vs 59 (gpt4)-28.4%
WinoGrande: 63.06 vs 87.5 (gpt4)-27.9%
GSM8K: 39.8 vs 96.4 (so35)-58.7%
LLME Score: 0.23952
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)
ValidateAI 3 33B Ties Parameters and Internals
| LLM Name | ValidateAI 3 33B Ties |
| Repository 🤗 | https://huggingface.co/arvindanand/ValidateAI-3-33B-Ties |
| Base Model(s) | |
| Model Size | 33b |
| Required VRAM | 66.5 GB |
| Updated | 2024-09-07 |
| Maintainer | arvindanand |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizerFast |
| Beginning of Sentence Token | <｜begin▁of▁sentence｜> |
| End of Sentence Token | <|EOT|> |
| Vocabulary Size | 32256 |
| Torch Data Type | float16 |
Best Alternatives to ValidateAI 3 33B Ties
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek Wizard 33B Slerp | 16K / 35.3 GB | 5 | 0 |
| Deepseek Coder 33B Instruct | 16K / 66.5 GB | 6906 | 437 |
| ValidateAI 2 33B AT | 16K / 66.5 GB | 5 | 0 |
| ...epseek Coder 33B Instruct AQLM | 2K / 9.6 GB | 6 | 3 |
| ...er 33B Instruct 4.0bpw H6 EXL2 | 16K / 17.1 GB | 15 | 5 |
| ...er 33B Instruct 8.0bpw H8 EXL2 | 16K / 33.6 GB | 7 | 3 |
| ...er 33B Instruct 3.0bpw H6 EXL2 | 16K / 13 GB | 8 | 1 |
| ...r 33B Instruct 4.65bpw H6 EXL2 | 16K / 19.8 GB | 8 | 1 |
| ...er 33B Instruct 5.0bpw H6 EXL2 | 16K / 21.2 GB | 8 | 1 |
| ...eepseek Coder 33B Instruct AWQ | 16K / 18.1 GB | 81024 | 35 |
Note: green Score (e.g. "73.2") means that the model is better than arvindanand/ValidateAI-3-33B-Ties .
Rank the ValidateAI 3 33B Ties 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803