Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3-med... Custom code Dataset:mlabonne/orpo-dpo-mix-... Endpoints compatible Instruct Model-index Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/BlackBeenie/Neos-Phi-3-14B-v0.1
Neos Phi 3 14B V0.1 Benchmarks
MMLU Pro: 39.6
GPQA: 7.38
MUSR: 10.53
BBH: 46.63
IFEval: 40.22 vs 88 (so35)-54.3%
MATH Lvl 5: 16.69
LLME Score: 0.33271
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)
Neos Phi 3 14B V0.1 Parameters and Internals
| LLM Name | Neos Phi 3 14B V0.1 |
| Repository 🤗 | https://huggingface.co/BlackBeenie/Neos-Phi-3-14B-v0.1 |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 28 GB |
| Updated | 2024-12-22 |
| Maintainer | BlackBeenie |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 32013 |
| Torch Data Type | bfloat16 |
Best Alternatives to Neos Phi 3 14B V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3 Medium 128K Instruct | 128K / 28 GB | 74641 | 373 |
| ...ess V2.5 Phi 3 Medium 128K 14B | 128K / 28 GB | 6701 | 3 |
| Finetuned Phi3 Medium 128K | 128K / 28 GB | 16 | 0 |
| Shisa V1 Phi3 14B | 128K / 28 GB | 16 | 2 |
| Mahou 1.2 Phi 14B | 128K / 28 GB | 14 | 1 |
| Phi 3 Medium 4K Instruct | 4K / 28 GB | 39236 | 211 |
| ...colatine 14B Instruct DPO V1.2 | 4K / 28 GB | 6942 | 14 |
| Ph3della5 14B | 4K / 28 GB | 2902 | 0 |
| ...ium 4K Instruct Abliterated V3 | 4K / 28 GB | 7123 | 22 |
| ...hocolatine 14B Instruct 4K DPO | 4K / 28 GB | 5238 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than BlackBeenie/Neos-Phi-3-14B-v0.1 .
Rank the Neos Phi 3 14B V0.1 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? 40123 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217