Arxiv:2401.18058 4-bit Autotrain compatible Awq Base model:quantized:thudm/lon... Base model:thudm/longalign-13b... Dataset:thudm/longalign-10k En Endpoints compatible Finetuned Llama Long context Pytorch Quantized Region:us Safetensors Zh
LongAlign 13B 64K 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)
LongAlign 13B 64K AWQ Parameters and Internals
| LLM Name | LongAlign 13B 64K AWQ |
| Repository 🤗 | https://huggingface.co/MaziyarPanahi/LongAlign-13B-64k-AWQ |
| Model Name | LongAlign-13B-64k-AWQ |
| Model Creator | THUDM |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 7.2 GB |
| Updated | 2024-09-16 |
| Maintainer | MaziyarPanahi |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.38.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32256 |
| Torch Data Type | float16 |
Best Alternatives to LongAlign 13B 64K AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yarn Llama 2 13B 128K AWQ | 128K / 7.2 GB | 15 | 2 |
| ...oboros L2 13B 2 1 YaRN 64K AWQ | 64K / 7.2 GB | 11 | 2 |
| OrcaMaid V3 13B 32K AWQ | 32K / 7.2 GB | 14 | 4 |
| OrcaMaid V2 FIX 13B 32K AWQ | 32K / 7.2 GB | 6 | 1 |
| NexusRaven V2 13B AWQ | 16K / 7.2 GB | 6 | 3 |
| ...th CodeLlama 13B Python Hf AWQ | 16K / 7.5 GB | 5 | 0 |
| WhiteRabbitNeo 13B AWQ | 16K / 7.2 GB | 7 | 4 |
| NexusRaven V2 13B AWQ | 16K / 7.2 GB | 22 | 1 |
| Ramgpt 13B AWQ Gemm | 16K / 7.2 GB | 0 | 1 |
| XwinCoder 13B AWQ | 16K / 7.2 GB | 11 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/LongAlign-13B-64k-AWQ .
Rank the LongAlign 13B 64K 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? 35926 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803