Semiconductor Llama3 V2 AWQ is an open-source language model by sitloboi2012. Features: 2b LLM, VRAM: 5.8GB, Context: 8K, Quantized.
| LLM Name | Semiconductor Llama3 V2 AWQ |
| Repository 🤗 | https://huggingface.co/sitloboi2012/semiconductor-llama3-v2_awq |
| Model Size | 2b |
| Required VRAM | 5.8 GB |
| Updated | 2024-07-04 |
| Maintainer | sitloboi2012 |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MiniCPM5 2B AWQ 8bit | 128K / 3.2 GB | 28 | 2 |
| MiniCPM5 2B AWQ 4bit | 128K / 2.2 GB | 34 | 1 |
| Drug Profile Llama 3 AWQ | 8K / 5.8 GB | 11 | 0 |
| ...t Agents Llama3 4.0.22 DPO AWQ | 8K / 5.8 GB | 7 | 0 |
| Llama3 AWQ Hermes 2 Theta | 8K / 5.8 GB | 6 | 0 |
| EPFL TA Meister AWQ 4bit | 8K / 5.8 GB | 7 | 0 |
| ...T Agents Llama3 5.0.77 DPO AWQ | 8K / 5.8 GB | 5 | 0 |
| MiniCPM5 2B Chat Mlx 4bit | 128K / 1.4 GB | 232 | 2 |
| MiniCPM5 2B 8bit | 128K / 2.7 GB | 734 | 6 |
| MiniCPM5 2B OptiQ 4bit | 128K / 1.9 GB | 317 | 3 |