Arxiv:2210.17323 Arxiv:2302.13971 4bit Autotrain compatible Endpoints compatible Llama Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/sardukar/llama13b-4bit-v2
Llama13b 4bit V2 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)
Llama13b 4bit V2 Parameters and Internals
| Model Type |
| |||||||
| Additional Notes |
| |||||||
| Release Notes |
|
| LLM Name | Llama13b 4bit V2 |
| Repository 🤗 | https://huggingface.co/sardukar/llama13b-4bit-v2 |
| Required VRAM | 7 GB |
| Updated | 2025-09-23 |
| Maintainer | sardukar |
| 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 Llama13b 4bit V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Panther V1 | 2K / 0 GB | 803 | 1 |
| BigTranslate | 0K / 26.5 GB | 865 | 50 |
| Toolpaca | 0K / 52.1 GB | 7 | 37 |
| Gpt4 X Alpaca | 0K / 52.1 GB | 6 | 1 |
| Guanaco Dumbdumb | 0K / 0 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than sardukar/llama13b-4bit-v2 .
Rank the Llama13b 4bit V2 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? 51534 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124