4bit Adapter Base model:adapter:meta-llama/... Base model:meta-llama/llama-2-... Dataset:izumi-lab/llm-japanese... Finetuned Ja Lora Peft Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese
Llama 2 70B Chat 4bit Japanese 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)
Llama 2 70B Chat 4bit Japanese Parameters and Internals
| Model Type |
| |||||||||
| Supported Languages |
| |||||||||
| Training Details |
|
| LLM Name | Llama 2 70B Chat 4bit Japanese |
| Repository 🤗 | https://huggingface.co/AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese |
| Base Model(s) | |
| Model Size | 70b |
| Required VRAM | 3.3 GB |
| Updated | 2024-12-22 |
| Maintainer | AIgroup-CVM-utokyohospital |
| Model Files | |
| Supported Languages | ja |
| Quantization Type | 4bit |
| Model Architecture | Adapter |
| License | llama2 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|o_proj|v_proj|gate_proj|k_proj|down_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.1 |
| R Param | 64 |
Best Alternatives to Llama 2 70B Chat 4bit Japanese
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama3 70b Ft | 0K / 39.9 GB | 6 | 0 |
| ...LM 2Bit QLoRA Function Calling | 0K / 0.1 GB | 13 | 7 |
| ...ma 2 70B Chat 4bit Japanese V1 | 0K / 3.3 GB | 3 | 4 |
| ...aiga Llama3 70b Sft M1 D5 Lora | 0K / 5.9 GB | 0 | 1 |
| Llama 3 70B Instruct Spider | 0K / 141.9 GB | 6 | 0 |
| Airoboros 70B 3.3 Peft | 0K / 0.4 GB | 0 | 2 |
| Llama3v1 | 0K / 0.1 GB | 5 | 0 |
| Xwin LM 70B V0.1 LORA | 0K / 1.7 GB | 0 | 1 |
| Euryale 1.3 L2 70B LORA | 0K / 1.7 GB | 3 | 1 |
| Miqu 1 70B Hermes2.5 Qlora | 0K / 4.8 GB | 0 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese .
Rank the Llama 2 70B Chat 4bit Japanese 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? 40123 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217