LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Eva Dolphin Llama3 8B Spanish by ecastera

 »  All LLMs  »  ecastera  »  Eva Dolphin Llama3 8B Spanish   URL Share it on

  27   
  4-bit   Autotrain compatible   Bitsandbytes Cognitivecomputations/dolphin-...   Conversational Dataset:bertin-project/alpaca-...   Dataset:ecastera/filosofia-es   Dataset:ecastera/wiki fisica   En   Endpoints compatible   Es   Español   Int8   Llama   Llama3   Lora   Mistral   Multilingual   Region:us   Safetensors   Spanish
Model Card on HF 🤗: https://huggingface.co/ecastera/eva-dolphin-llama3-8b-spanish 

Eva Dolphin Llama3 8B Spanish Benchmarks

LLME Score: 0.18532
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Eva Dolphin Llama3 8B Spanish (ecastera/eva-dolphin-llama3-8b-spanish)

Eva Dolphin Llama3 8B Spanish Parameters and Internals

Model Type 
text generation, multilingual
Use Cases 
Areas:
research, multilingual applications
Applications:
multilingual text generation, logic and reasoning tasks
Primary Use Cases:
High quality Spanish text generation
Additional Notes 
Fine-tuned for Spanish high quality text generation, especially for conversation, utilizing a variety of Spanish sources.
Supported Languages 
es (High Quality), en (Basic)
Training Details 
Data Sources:
ecastera/wiki_fisica, ecastera/filosofia-es, bertin-project/alpaca-spanish
Methodology:
Fine-tuned using QLora and PEFT and INT4 quantization.
Input Output 
Accepted Modalities:
text
Performance Tips:
Run inference in INT8 or INT4 mode for efficiency.
LLM NameEva Dolphin Llama3 8B Spanish
Repository 🤗https://huggingface.co/ecastera/eva-dolphin-llama3-8b-spanish 
Model Size8b
Required VRAM0.3 GB
Updated2025-02-22
Maintainerecastera
Model Files  0.3 GB
Supported Languageses en
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|down_proj|up_proj|q_proj|gate_proj|k_proj|o_proj
LoRA Alpha16
LoRA Dropout0.1
R Param32

Best Alternatives to Eva Dolphin Llama3 8B Spanish

Best Alternatives
Context / RAM
Downloads
Likes
Trillama 8B8K / 16.1 GB1793
AutogenJune20008K / 33.8 GB70
Llama3 8B8K / 16.1 GB50
Medllama3 V200K / 16.1 GB2563169
Autotrain Pvqlj Odah20K / 0.2 GB180
500tiao 100lun0K / 0.2 GB70
Codelica0K / 16.1 GB1110
ModeliCo 8B0K / 16.1 GB112
TalktoaiQT0K / 16.1 GB332
MotherEarth Proverbs 1.0 8B0K / 16.1 GB200
Note: green Score (e.g. "73.2") means that the model is better than ecastera/eva-dolphin-llama3-8b-spanish.

Rank the Eva Dolphin Llama3 8B Spanish 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! 🌟

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? 43470 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer