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

Gradientai Llama 3 8B Instruct 262K V2 EXL2 6.0bpw by bullerwins

 »  All LLMs  »  bullerwins  »  Gradientai Llama 3 8B Instruct 262K V2 EXL2 6.0bpw   URL Share it on

  14   
  Arxiv:2305.14233   Arxiv:2309.00071   Arxiv:2402.08268   6-bit   Autotrain compatible   Conversational   En   Endpoints compatible   Exl2   Instruct   Llama   Llama-3   Meta   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/bullerwins/gradientai_Llama-3-8B-Instruct-262k_v2_exl2_6.0bpw 

Gradientai Llama 3 8B Instruct 262k V2 EXL2 6.0bpw Benchmarks

LLME Score: 0.1948
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gradientai Llama 3 8B Instruct 262K V2 EXL2 6.0bpw (bullerwins/gradientai_Llama-3-8B-Instruct-262k_v2_exl2_6.0bpw)

Gradientai Llama 3 8B Instruct 262K V2 EXL2 6.0bpw Parameters and Internals

Model Type 
text generation, instruction-tuned
Use Cases 
Areas:
commercial, research
Applications:
assistant-like chat
Primary Use Cases:
natural language generation tasks
Limitations:
English only; out-of-scope for illegal or prohibited use cases
Considerations:
Developers may fine-tune for languages beyond English adhering to specific policies.
Additional Notes 
The model is intended for English-language applications and could be adapted for other languages.
Supported Languages 
languages_supported (English), proficiency ()
Training Details 
Data Sources:
SlimPajama, UltraChat
Data Volume:
15 trillion tokens
Methodology:
Supervised fine-tuning, reinforcement learning with human feedback (RLHF)
Context Length:
262144
Hardware Used:
Crusoe Energy high performance L40S cluster
Model Architecture:
Transformer with improved RoPE theta, NTK-aware interpolation
Safety Evaluation 
Methodologies:
red teaming, adversarial evaluations
Risk Categories:
misinformation, bias, cybersecurity, child safety
Ethical Considerations:
Iterative testing for CBRNE threats
Responsible Ai Considerations 
Fairness:
Model is optimized for safety and helpfulness but trade-offs exist.
Transparency:
Steps for safety best practices outlined in Responsible Use Guide.
Accountability:
Meta
Mitigation Strategies:
Meta Llama Guard 2 and Code Shield provided for safety tailored applications
Input Output 
Input Format:
text input
Accepted Modalities:
text
Output Format:
text generation
Release Notes 
Version:
5/3/2024
Date:
2024-05-03
Notes:
Further fine-tuned for assistant-like chat ability; extended context length.
LLM NameGradientai Llama 3 8B Instruct 262k V2 EXL2 6.0bpw
Repository 🤗https://huggingface.co/bullerwins/gradientai_Llama-3-8B-Instruct-262k_v2_exl2_6.0bpw 
Model Size8b
Required VRAM6.7 GB
Updated2024-12-22
Maintainerbullerwins
Model Typellama
Instruction-BasedYes
Model Files  6.7 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length262144
Model Max Length262144
Transformers Version4.41.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Gradientai Llama 3 8B Instruct 262K V2 EXL2 6.0bpw

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB152
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB121
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB82
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1425
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB3417
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB143
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB91
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB91
...B Instruct 262k V2 EXL2 5.0bpw256K / 5.8 GB101
Note: green Score (e.g. "73.2") means that the model is better than bullerwins/gradientai_Llama-3-8B-Instruct-262k_v2_exl2_6.0bpw.

Rank the Gradientai Llama 3 8B Instruct 262K V2 EXL2 6.0bpw 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? 40066 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 v20241217
  Support LLM Explorer