Arxiv:2404.01657 4bit Autotrain compatible Dataset:databricks/databricks-... Dataset:izumi-lab/llm-japanese... Dataset:kunishou/databricks-do... En Gptq Ja Llama Quantized Region:us
Youri 7B Chat Gptq Parameters and Internals
| LLM Name | Youri 7B Chat Gptq |
| Repository | Open on 🤗 |
| Model Size | 7b |
| Required VRAM | 3.9 GB |
| Updated | 2024-07-27 |
| Maintainer | rinna |
| Model Type | llama |
| Model Files | |
| Supported Languages | ja en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Youri 7B Chat Gptq
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Yarn Llama 2 7B 128K GPTQ | 0.2 | 128K / 3.9 GB | 23 | 7 |
| Yarn Llama 2 7B 64K GPTQ | 0.2 | 64K / 3.9 GB | 10 | 1 |
| ... 7B 32K Instructions V4 Marlin | 0.2 | 32K / 4.1 GB | 26 | 0 |
| Aixcoder 7B GPTQ | 0.2 | 32K / 4.5 GB | 6 | 1 |
| Calm2 7B Chat GPTQ | 0.2 | 32K / 4.4 GB | 13 | 6 |
| ...Calm2 7B Chat GPTQ Calib Ja 1K | 0.2 | 32K / 4.4 GB | 10 | 5 |
| Llama 2 7B 32K Instruct GPTQ | 0.2 | 32K / 3.9 GB | 60 | 27 |
| CodeLlama 7B Instruct GPTQ | 0.2 | 16K / 3.9 GB | 53579 | 42 |
| Codebear 7B 4bit | 0.2 | 16K / 3.9 GB | 10 | 1 |
| ...a 7B Instruct GPTQ Calib Ja 1K | 0.2 | 16K / 3.9 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than rinna/youri-7b-chat-gptq .
Rank the Youri 7B Chat Gptq 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501