Arxiv:1910.09700 Base model:finetune:openlm-res... Base model:openlm-research/ope... Llama Pytorch Region:us
Model Card on HF 🤗: https://huggingface.co/sakhan10/quantized_open_llama_3b_v2
Quantized Open Llama 3b 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)
Quantized Open Llama 3B V2 Parameters and Internals
| LLM Name | Quantized Open Llama 3b V2 |
| Repository 🤗 | https://huggingface.co/sakhan10/quantized_open_llama_3b_v2 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 3.7 GB |
| Updated | 2025-01-14 |
| Maintainer | sakhan10 |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.44.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Quantized Open Llama 3B V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1185899 | 893 |
| Llama 3.2 3B | 128K / 6.5 GB | 402381 | 456 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 21469 | 125 |
| Orca Mini V9 5 3B Instruct | 128K / 6.5 GB | 354 | 6 |
| Dolphin3.0 Llama3.2 3B | 128K / 6.5 GB | 4816 | 23 |
| Llama Deepsync 3B | 128K / 6.5 GB | 407 | 15 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 2651 | 1 |
| Llama 3.2 Korean Bllossom 3B | 128K / 6.5 GB | 22005 | 140 |
| Orca Mini V9 6 3B Instruct | 128K / 6.5 GB | 60 | 4 |
| Llama 3.2 3B RP DeepThink | 128K / 7.2 GB | 221 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than sakhan10/quantized_open_llama_3b_v2 .
Rank the Quantized Open Llama 3B 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? 41473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227