Arxiv:1910.09700 4bit Autotrain compatible Conversational Endpoints compatible Finetuned Instruct Mistral Pytorch Quantized Region:us Sft Sharded Trl Unsloth
Phi3 Finetune Test Parameters and Internals
| LLM Name | Phi3 Finetune Test |
| Repository | Open on 🤗 |
| Required VRAM | 7.6 GB |
| Updated | 2024-07-27 |
| Maintainer | XOneThree |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Phi3 Finetune Test
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ... Mini 4K Instruct Bnb 4bit Ita | 0.3 | 4K / 7.6 GB | 1981 | 0 |
| ...ini New Model With Lora Merged | 0.3 | 4K / 7.6 GB | 52 | 0 |
| Phired | 0.3 | 4K / 7.6 GB | 29 | 0 |
| Phi 3 Mini Hospital Topic 50 | 0.2 | 4K / 7.6 GB | 16 | 0 |
| Model | 0.2 | 4K / 7.6 GB | 19 | 0 |
| Phi3 History V2 | 0.2 | 4K / 7.6 GB | 7 | 0 |
| Model | 0.2 | 4K / 7.6 GB | 9 | 0 |
| MainPHI3 | 0.2 | 4K / 7.6 GB | 6 | 0 |
| Phi3 StoryGenerator | 0.2 | 4K / 7.6 GB | 34 | 2 |
| MediChat Revision | 0.2 | 4K / 7.6 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than XOneThree/phi3-finetune-test .
Rank the Phi3 Finetune Test 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