Suzume Llama 3 8B Multilingual by AlekseyElygin

 ยป  All LLMs  ยป  AlekseyElygin  ยป  Suzume Llama 3 8B Multilingual   URL Share it on

Base model:lightblue/suzume-ll... Base model:quantized:lightblue...   Conversational   En   Endpoints compatible   Gguf   Llama   Lora   Quantized   Region:us   Trl   Unsloth

Suzume Llama 3 8B Multilingual Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Suzume Llama 3 8B Multilingual (AlekseyElygin/suzume-llama-3-8B-multilingual)

Suzume Llama 3 8B Multilingual Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, llama, trl
Additional Notes 
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameSuzume Llama 3 8B Multilingual
Repository ๐Ÿค—https://huggingface.co/AlekseyElygin/suzume-llama-3-8B-multilingual 
Base Model(s)  Suzume Llama 3 8B Multilingual   lightblue/suzume-llama-3-8B-multilingual
Model Size8b
Required VRAM4.9 GB
Updated2024-12-22
MaintainerAlekseyElygin
Model Files  4.9 GB   5.7 GB   8.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0
Model Max Length8192
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|up_proj|down_proj|gate_proj|o_proj|k_proj|q_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Suzume Llama 3 8B Multilingual

Best Alternatives
Context / RAM
Downloads
Likes
Meta Llama 3 8B Instruct GGUF0K / 2 GB202286177
...ma 3 8B Instruct 32K V0.1 GGUF0K / 2 GB201466056
Llama 3.1 8B Open SFT GGUF0K / 4.9 GB896
Llama 3 8B Instruct 64K GGUF0K / 3.2 GB195499312
OpenMath 8B GGUF0K / 4.9 GB5117
...B Instruct Bnb 4bit 24 1 100 10K / 16.1 GB280
CleverBoi Llama 3.1 8B V20K / 16.1 GB1170
...leverBoi Llama 3.1 8B Instruct0K / 0.2 GB2191
Granite 8B Code Instruct GGUF0K / 3.1 GB182506
Llama 3 Smaug 8B GGUF0K / 3.2 GB311234
Note: green Score (e.g. "73.2") means that the model is better than AlekseyElygin/suzume-llama-3-8B-multilingual.

Rank the Suzume Llama 3 8B Multilingual 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  

What open-source LLMs or SLMs are you in search of? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217