Autotrain compatible Chocolatine Conversational Custom code Dataset:jpacifico/french-orca-... En Endpoints compatible Fr French Instruct Phi3 Region:us Safetensors Sharded Tensorflow
Chocolatine 3B Instruct DPO Revised Benchmarks
MMLU Pro: 33.21
GPQA: 9.62
MUSR: 15.1
BBH: 37.16
IFEval: 56.23 vs 88 (so35)-36.1%
MATH Lvl 5: 14.5
LLME Score: 0.36052
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)
Chocolatine 3B Instruct DPO Revised Parameters and Internals
| LLM Name | Chocolatine 3B Instruct DPO Revised |
| Repository 🤗 | https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-Revised |
| Model Size | 3b |
| Required VRAM | 7.7 GB |
| Updated | 2024-10-16 |
| Maintainer | jpacifico |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | fr en |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Chocolatine 3B Instruct DPO Revised
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ocolatine 3B Instruct DPO V1.2 | 128K / 7.7 GB | 41 | 2 |
| ECE EIFFEL 3B | 128K / 7.7 GB | 17 | 0 |
| ECE GRENELLE 3B | 128K / 7.7 GB | 60 | 0 |
| Phi3 3B Ultrachat Svd Model | 128K / 7.7 GB | 4 | 1 |
| Orpo Phi3 3B 128K | 128K / 7.7 GB | 24 | 4 |
| ECE EIFFEL 3Bv3 | 4K / 7.7 GB | 13 | 0 |
| ...ocolatine 3B Instruct DPO V1.0 | 4K / 7.7 GB | 89 | 2 |
| Redhen Lab News Chat 3B | 4K / 7.7 GB | 5 | 0 |
| Phi 3 Mini 4K Instruct DPO | 4K / 7.7 GB | 27 | 3 |
Rank the Chocolatine 3B Instruct DPO Revised 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? 36894 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803