Arxiv:2401.13303 Base model:finetune:meta-llama... Base model:meta-llama/llama-2-... Dataset:cis-lmu/glot500 Endpoints compatible Lora Multilingual Region:us
Mala 500 10B V1 Parameters and Internals
| LLM Name | Mala 500 10B V1 |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.3 GB |
| Updated | 2024-07-27 |
| Maintainer | MaLA-LM |
| Model Files | |
| Model Architecture | AutoModel |
| License | llama2 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.1 |
| R Param | 8 |
Best Alternatives to Mala 500 10B V1
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| TroL 7B | 0.3 | 32K / 17.3 GB | 647 | 6 |
| MoAI 7B | 0.3 | 32K / 17.7 GB | 2314 | 45 |
| CoLLaVO 7B | 0.2 | 32K / 18.6 GB | 335 | 21 |
| ... 7b 448 Qinstruct Preview V0.1 | 0.2 | 2K / 17.3 GB | 11 | 4 |
| ...Tulu2 7b Writing Prompts 32768 | 0.3 | 0K / 8.5 GB | 74 | 0 |
| Silicon Natsuki 7B | 0.2 | 0K / 14.4 GB | 8 | 1 |
| Medical Mixtral 7B V2k | 0.2 | 0K / 0.4 GB | 7 | 0 |
| Diff Starcoder 7B Rl | 0.2 | 0K / 0.1 GB | 6 | 0 |
| Mistral 7B Instruct V0.2 ONNX | 0.2 | 0K / GB | 37 | 4 |
| Rolema 7B It | 0.2 | 0K / 0.8 GB | 0 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than MaLA-LM/mala-500-10b-v1 .
Rank the Mala 500 10B V1 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