Arxiv:1910.09700 Autotrain compatible Conversational Custom code Endpoints compatible Instruct Llama-factory Lora Phi3 Region:us Safetensors Sharded Tensorflow
Rank the Phi3 Lora Ktomixen Post Sft Mathinstruct Lima Partial 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! 🌟
Best Alternatives to Phi3 Lora Ktomixen Post Sft Mathinstruct Lima Partial
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Phi3 4K | 69.6 | 4K / 7.7 GB | 34 | 1 |
| ...hi 3 Medical Instruct Themanas | — | 128K / 4 GB | 186 | 1 |
| Phi 3 Mini 128K Instruct FP8 | — | 128K / 4 GB | 709 | 0 |
| Phi Marketing | — | 128K / 7.6 GB | 256 | 1 |
| ...i 3 Mini 128K Function Calling | — | 128K / 7.6 GB | 139 | 1 |
| Phi3 Presidents | — | 128K / 7.6 GB | 25 | 0 |
| Phi3 MoE | — | 128K / 7.6 GB | 23 | 0 |
| ...hi3 Lora Post Sft Kto Sft Qasc | — | 128K / 7.6 GB | 10 | 0 |
| ...hi3 Lora Sft Mathinstruct Lima | — | 128K / 7.6 GB | 7 | 0 |
| Phi 3 Mini 128K Instruct | — | 128K / 7.7 GB | 2068251 | 1441 |
Note: green Score (e.g. "73.2") means that the model is better than ghemdd/phi3_lora_ktomixen_post_sft-mathinstruct-lima_partial .
Phi3 Lora Ktomixen Post Sft Mathinstruct Lima Partial Parameters and Internals
| LLM Name | Phi3 Lora Ktomixen Post Sft Mathinstruct Lima Partial |
| Repository | Open on 🤗 |
| Model Size | 3.8b |
| Required VRAM | 7.6 GB |
| Updated | 2024-07-07 |
| Maintainer | ghemdd |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| LoRA Model | Yes |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
| Embedding Dropout | 0 |
What open-source LLMs or SLMs are you in search of? 34531 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801