Llama3 Mj Ko 8B by mintaeng

 ยป  All LLMs  ยป  mintaeng  ยป  Llama3 Mj Ko 8B   URL Share it on

  Arxiv:1910.09700   Autotrain compatible   Conversational   Endpoints compatible   Llama   Lora   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth

Rank the Llama3 Mj Ko 8B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  
Llama3 Mj Ko 8B (mintaeng/llama3-mj-ko-8b)

Best Alternatives to Llama3 Mj Ko 8B

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...olphin Llama3 Zh Cn Uncensored57.70K / 16.1 GB167610
... 3 Instruct Bellman 8B Swedish0K / 0 GB4492
...Openwebtext Distilled 80K Gpt40K / 0 GB2590
Llama5p0K / 0 GB320
Best 8b0K / 0.1 GB70
Llama3 8B Hikikomori V0.30K / 0.2 GB5574
Llama 3 8B Chat FAQ0K / 0.2 GB70
Llama 3 8B Movie Chatbot0K / 0.2 GB60
Eva Dolphin Llama3 8B Spanish0K / 0.3 GB601
... Meta Llama 3 8B Instruct Lora0K / 0.7 GB113
Note: green Score (e.g. "73.2") means that the model is better than mintaeng/llama3-mj-ko-8b.

Llama3 Mj Ko 8B Parameters and Internals

LLM NameLlama3 Mj Ko 8B
RepositoryOpen on ๐Ÿค— 
Model Size8b
Required VRAM16.3 GB
Updated2024-06-24
Maintainermintaeng
Model Files  0.3 GB   5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.4 GB: 4-of-4
Model ArchitectureAutoModelForCausalLM
Model Max Length8192
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj|o_proj|q_proj|k_proj|up_proj|v_proj|gate_proj
LoRA Alpha64
LoRA Dropout0.05
R Param32

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801