Model Card on HF 🤗: https://huggingface.co/wcde/llama-7b-4bit-gr128
Llama 7B 4bit Gr128 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)
Llama 7B 4bit Gr128 Parameters and Internals
| Additional Notes |
|
| LLM Name | Llama 7B 4bit Gr128 |
| Repository 🤗 | https://huggingface.co/wcde/llama-7b-4bit-gr128 |
| Model Size | 7b |
| Required VRAM | 4 GB |
| Updated | 2025-02-05 |
| Maintainer | wcde |
| Model Type | llama |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LLaMAForCausalLM |
| Transformers Version | 4.27.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llama 7B 4bit Gr128
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 7B Onnx Merged Fp16 | 2K / GB | 7 | 7 |
| Alpaca 7B Native 4bit | 0K / 4.5 GB | 11 | 4 |
| Alpaca Native 4bit | 0K / 4.5 GB | 20 | 58 |
| Llama 7B 4bit Act | 0K / 3.8 GB | 5 | 2 |
| Swallow 7B GPTQ | 4K / 4.1 GB | 11 | 1 |
| Honest Llama2 Chat 7B | 2K / 13.5 GB | 81 | 9 |
| Llama 7B Onnx Merged Fp32 | 2K / GB | 6 | 2 |
| Chatdoctor | 0K / 27 GB | 1232 | 11 |
| ...xplore LM Ext 7B Brainstorming | 0K / 27 GB | 11 | 2 |
| Explore LM Ext 7B Rewriting | 0K / 27 GB | 10 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than wcde/llama-7b-4bit-gr128 .
Rank the Llama 7B 4bit Gr128 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227