Arxiv:2307.09288 Arxiv:2404.01657 Autotrain compatible Dataset:databricks/databricks-... Dataset:izumi-lab/llm-japanese... Dataset:kunishou/databricks-do... En Instruct Ja Llama Pytorch Region:us Safetensors
Youri 7B Instruction Parameters and Internals
| LLM Name | Youri 7B Instruction |
| Repository | Open on 🤗 |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2024-07-27 |
| Maintainer | rinna |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ja en |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Quantized Models of the Youri 7B Instruction
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Youri 7B Instruction Gptq | 7 | 495 | 3 GB |
Best Alternatives to Youri 7B Instruction
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Llama 2 7B 32K Instruct | 0.3 | 32K / 13.5 GB | 9799 | 160 |
| Qwen2 7B Instruct Llama | 0.2 | 32K / 15.2 GB | 13 | 2 |
| Qwen2 7B Instruct Mistral | 0.2 | 32K / 15.2 GB | 11 | 1 |
| AIRIC The Mistral | 0.2 | 32K / 14.4 GB | 936 | 6 |
| ...ls Vikhr 7B Instruct 0.4 4bits | 0.2 | 32K / 5.2 GB | 8 | 0 |
| Vikhr 7B Instruct 0.3 | 0.2 | 32K / 14.6 GB | 19 | 4 |
| ... Samantha Philosopher 7B Slerp | 0.2 | 32K / 13.4 GB | 7 | 2 |
| Vikhr 7B Instruct Merged | 0.2 | 32K / 14.6 GB | 6 | 4 |
| Clinical Ehr Prototype 0.1 | 0.2 | 32K / 14.4 GB | 10 | 1 |
| ...stral 7B Instruct V0.1 Sharded | 0.2 | 32K / 14.4 GB | 2852 | 13 |
Note: green Score (e.g. "73.2") means that the model is better than rinna/youri-7b-instruction .
Rank the Youri 7B Instruction 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501