Autotrain compatible Code Conversational En Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow
Phi 3 Mini 4K Instruct LLaMAfied Benchmarks
ARC: 62.88 vs 96.7 (so35)-35%
HellaSwag: 80.57 vs 95.3 (gpt4)-15.5%
MMLU: 67.23 vs 88.3 (so35)-23.9%
TruthfulQA: 59.88 vs 59 (gpt4)1.5%
WinoGrande: 72.69 vs 87.5 (gpt4)-16.9%
GSM8K: 73.69 vs 96.4 (so35)-23.6%
LLME Score: 0.23591
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)
Phi 3 Mini 4K Instruct LLaMAfied Parameters and Internals
| LLM Name | Phi 3 Mini 4K Instruct LLaMAfied |
| Repository 🤗 | https://huggingface.co/vonjack/Phi-3-mini-4k-instruct-LLaMAfied |
| Model Size | 3.8b |
| Required VRAM | 7.6 GB |
| Updated | 2024-09-16 |
| Maintainer | vonjack |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.40.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 3 Mini 4K Instruct LLaMAfied
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3.5 Mini Instruct | 128K / 7.6 GB | 12973 | 37 |
| Llamaphi 3 128K Instruct | 128K / 7.6 GB | 80 | 0 |
| ...3 Mini 128K Instruct LLaMAfied | 128K / 7.6 GB | 6 | 2 |
| Phillama 3.8B V0.1 | 4K / 7.6 GB | 3 | 10 |
| Phillama 3.8B V1 | 4K / 7.6 GB | 4 | 5 |
| ...nder Llamafied With 16bit GGUF | 4K / 7.6 GB | 70 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than vonjack/Phi-3-mini-4k-instruct-LLaMAfied .
Rank the Phi 3 Mini 4K Instruct LLaMAfied 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803