Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Llama Lora Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Llama3 Mj Ko 8B Parameters and Internals
| LLM Name | Llama3 Mj Ko 8B |
| Repository | Open on 🤗 |
| Model Size | 8b |
| Required VRAM | 16.3 GB |
| Updated | 2024-07-27 |
| Maintainer | mintaeng |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 8192 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|o_proj|q_proj|k_proj|up_proj|v_proj|gate_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
Best Alternatives to Llama3 Mj Ko 8B
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Trillama 8B | 0.3 | 8K / 16.1 GB | 364 | 3 |
| Llama3 8B | 0.2 | 8K / 16.1 GB | 5 | 0 |
| Medllama3 V20 | 0.3 | 0K / 16.1 GB | 7070 | 19 |
| Meta Llama 3.1 8B Instruct OAS | 0.3 | 0K / 16.1 GB | 190 | 1 |
| Medical Llama3 V2 | 0.3 | 0K / 16.1 GB | 249 | 2 |
| Bella 1 8B | 0.3 | 0K / 32.1 GB | 167 | 2 |
| Llama3 Medqa | 0.3 | 0K / 9.1 GB | 1931 | 0 |
| Llama3 Openhermes 2.5 | 0.3 | 0K / 16.1 GB | 252 | 2 |
| NewMes V15 | 0.3 | 0K / 16.1 GB | 291 | 5 |
| ...Openwebtext Distilled 80K Gpt4 | 0.3 | 0K / 0 GB | 282 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mintaeng/llama3-mj-ko-8b .
Rank the Llama3 Mj Ko 8B 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