Model Card on HF 🤗: https://huggingface.co/ozcur/alpaca-native-4bit
Alpaca Native 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)
Alpaca Native 4bit Parameters and Internals
| Additional Notes |
|
| LLM Name | Alpaca Native 4bit |
| Repository 🤗 | https://huggingface.co/ozcur/alpaca-native-4bit |
| Model Size | 7b |
| Required VRAM | 4.5 GB |
| Updated | 2024-12-14 |
| Maintainer | ozcur |
| Model Type | llama |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LLaMAForCausalLM |
| Model Max Length | 512 |
| Transformers Version | 4.27.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32001 |
| Torch Data Type | float32 |
Best Alternatives to Alpaca Native 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 7B Onnx Merged Fp16 | 2K / GB | 13 | 7 |
| Alpaca 7B Native 4bit | 0K / 4.5 GB | 19 | 4 |
| Llama 7B 4bit Gr128 | 0K / 4 GB | 14 | 4 |
| Llama 7B 4bit Act | 0K / 3.8 GB | 12 | 2 |
| Swallow 7B GPTQ | 4K / 4.1 GB | 19 | 1 |
| Honest Llama2 Chat 7B | 2K / 13.5 GB | 201 | 9 |
| Llama 7B Onnx Merged Fp32 | 2K / GB | 14 | 2 |
| ...xplore LM Ext 7B Brainstorming | 0K / 27 GB | 11 | 2 |
| Explore LM Ext 7B Rewriting | 0K / 27 GB | 10 | 1 |
| Explore LM Ext 7B Math | 0K / 27 GB | 13 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ozcur/alpaca-native-4bit .
Rank the Alpaca Native 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? 39237 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124