Arxiv:1910.09700 Autotrain compatible Conversational Custom code Endpoints compatible Instruct Phi3 Region:us Safetensors Sharded Tensorflow
Phi3 4K Benchmarks
Phi3 4K Parameters and Internals
| LLM Name | Phi3 4K |
| Repository | Open on 🤗 |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2024-07-27 |
| Maintainer | ehartford |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi3 4K
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Phi 3 Mini 128K Instruct | 0.6 | 128K / 7.7 GB | 1167791 | 1497 |
| Phi 3 Mini 128K Instruct FP8 | 0.3 | 128K / 4 GB | 4742 | 0 |
| Phi 3 Mini 128K Back To Base | 0.3 | 128K / 7.7 GB | 11 | 2 |
| ...i 128K Instruct Abliterated V3 | 0.3 | 128K / 7.7 GB | 1340 | 10 |
| SeaPhi3 Mini | 0.3 | 128K / 7.7 GB | 3246 | 4 |
| ...ruct LinearBunkaScore 4.6K DPO | 0.3 | 128K / 7.7 GB | 471 | 2 |
| Phi 3 Mini 128K Instruct RU | 0.3 | 128K / 7.7 GB | 186 | 4 |
| ...ersedLinearBunkaScore 4.6K DPO | 0.3 | 128K / 7.7 GB | 466 | 0 |
| ...truct Simpo Lr 5e 07 Gamma 1.5 | 0.3 | 128K / 7.7 GB | 100 | 0 |
| ...K Peft Finetuned 20000 Dataset | 0.3 | 128K / 15.4 GB | 62 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ehartford/phi3-4k .
Rank the Phi3 4K 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501