Arxiv:1910.09700 4-bit 4bit Autotrain compatible Conversational Custom code Ext 8k Gptq Instruct Phi3small Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/stan-hua/Phi-3-small-7B-Instruct-GPTQ-4bit
Phi 3 Small 7B Instruct GPTQ 4bit Benchmarks
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 Small 7B Instruct GPTQ 4bit Parameters and Internals
| LLM Name | Phi 3 Small 7B Instruct GPTQ 4bit |
| Repository 🤗 | https://huggingface.co/stan-hua/Phi-3-small-7B-Instruct-GPTQ-4bit |
| Model Size | 7b |
| Required VRAM | 4.5 GB |
| Updated | 2025-02-22 |
| Maintainer | stan-hua |
| Model Type | phi3small |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Context Length | 8k |
| Quantization Type | gptq|4bit |
| Model Architecture | Phi3SmallForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Phi3SmallTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 100352 |
| Torch Data Type | float16 |
Rank the Phi 3 Small 7B Instruct GPTQ 4bit 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227