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

Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2 by blockblockblock

 »  All LLMs  »  blockblockblock  »  Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2   URL Share it on

  10   
  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/blockblockblock/Llama-3-8B-Instruct-Gradient-1048k-bpw6-exl2 

Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2 Benchmarks

ARC: 54.44 vs 96.7 (so35)-43.7%
HellaSwag: 76.77 vs 95.3 (gpt4)-19.4%
MMLU: 61.92 vs 88.3 (so35)-29.9%
TruthfulQA: 49.26 vs 59 (gpt4)-16.5%
WinoGrande: 72.3 vs 87.5 (gpt4)-17.4%
GSM8K: 44.35 vs 96.4 (so35)-54%
LLME Score: 0.17151
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2 (blockblockblock/Llama-3-8B-Instruct-Gradient-1048k-bpw6-exl2)
🌟 Advertise your project 🚀

Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial use, research
Applications:
assistant-like chat, natural language generation tasks
Primary Use Cases:
pretrained: general language generation, tuned: chat and assistance
Limitations:
Out-of-scope uses that violate policies or laws, limited to English
Considerations:
Possible inaccuracies, biases, and objectionable content.
Additional Notes 
Supports long contexts over 1040K.
Supported Languages 
English (full)
Training Details 
Data Sources:
SlimPajama, UltraChat
Data Volume:
1.4B tokens total for all stages
Methodology:
NTK-aware interpolation for RoPE theta, progressive training on increasing context lengths
Context Length:
1048
Hardware Used:
NVIDIA L40S
Model Architecture:
auto-regressive transformer with RingAttention
Safety Evaluation 
Methodologies:
extensive red teaming, adversarial evaluations
Risk Categories:
CBRNE, Cyber Security, Child Safety
Ethical Considerations:
Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
Responsible Ai Considerations 
Fairness:
Safety benchmark standards transparency, comprehensive safety safeguards.
Transparency:
Open approach to AI with community involvement.
Accountability:
Developers responsible for safety deployment based on use case.
Mitigation Strategies:
Use of Purple Llama solutions, thorough safety guides.
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text, code
Performance Tips:
Use supervised fine-tuning and reinforcement learning with human feedback for optimal results.
LLM NameLlama 3 8B Instruct Gradient 1048K Bpw6 EXL2
Repository 🤗https://huggingface.co/blockblockblock/Llama-3-8B-Instruct-Gradient-1048k-bpw6-exl2 
Base Model(s)  ... Instruct Gradient 1048K Agent   AIGym/Llama-3-8B-Instruct-Gradient-1048k-Agent
Model Size8b
Required VRAM6.7 GB
Updated2025-09-23
Maintainerblockblockblock
Model Typellama
Instruction-BasedYes
Model Files  6.7 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length1048576
Model Max Length1048576
Transformers Version4.41.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB62
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB61
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB17225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB10417
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB103
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB31
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB71
...B Instruct 262k V2 EXL2 5.0bpw256K / 5.8 GB61
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB61
Note: green Score (e.g. "73.2") means that the model is better than blockblockblock/Llama-3-8B-Instruct-Gradient-1048k-bpw6-exl2.

Rank the Llama 3 8B Instruct Gradient 1048K Bpw6 EXL2 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? 51544 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 v20241124
  Support LLM Explorer