Arxiv:2307.11760 4-bit Autotrain compatible Awq Base model:quantized:sophosymp... Base model:sophosympatheia/aur... En Llama Quantized Region:us Safetensors Sharded Tensorflow
Aurora Nights 70B V1.0 AWQ 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)
Aurora Nights 70B V1.0 AWQ Parameters and Internals
| LLM Name | Aurora Nights 70B V1.0 AWQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Aurora-Nights-70B-v1.0-AWQ |
| Model Name | Aurora Nights 70B v1.0 |
| Model Creator | Sophosympatheia |
| Base Model(s) | |
| Model Size | 70b |
| Required VRAM | 36.6 GB |
| Updated | 2024-10-18 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Aurora Nights 70B V1.0 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...0B Instruct Gradient 1048K AWQ | 1024K / 39.9 GB | 6 | 1 |
| ...70B Instruct Gradient 262K AWQ | 256K / 39.9 GB | 5 | 0 |
| MultiVerse 70B AWQ | 32K / 41.3 GB | 67 | 2 |
| Opus V1.2 70B AWQ | 32K / 36.7 GB | 6 | 1 |
| QuartetAnemoi 70B T0.0001 AWQ | 31K / 36.7 GB | 2 | 1 |
| Senku 70B AWQ 4bit GEMM | 31K / 36.7 GB | 4 | 1 |
| Kiqu 70B AWQ | 31K / 36.7 GB | 7 | 1 |
| CodeLlama 70B Hf AWQ | 16K / 36.6 GB | 14 | 4 |
| Llama 3 70B Instruct AWQ | 8K / 39.9 GB | 9958 | 66 |
| ...Typhoon V1.5x 70B Instruct AWQ | 8K / 39.9 GB | 3041 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Aurora-Nights-70B-v1.0-AWQ .
Rank the Aurora Nights 70B V1.0 AWQ 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803