Llama3 Turbcat Instruct 8B Bpw2.5 EXL2 by blockblockblock

 ยป  All LLMs  ยป  blockblockblock  ยป  Llama3 Turbcat Instruct 8B Bpw2.5 EXL2   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Exl2   Instruct   Llama   Quantized   Region:us   Safetensors

Llama3 Turbcat Instruct 8B Bpw2.5 EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 Turbcat Instruct 8B Bpw2.5 EXL2 (blockblockblock/llama3-turbcat-instruct-8b-bpw2.5-exl2)

Llama3 Turbcat Instruct 8B Bpw2.5 EXL2 Parameters and Internals

Model Type 
text generation, roleplay
Use Cases 
Areas:
research, commercial applications
Applications:
text generation, roleplay API usage
Primary Use Cases:
text generation, roleplaying in APIs
Limitations:
Limited Chinese support compared to English, Based on base model choice
Additional Notes 
Join Discord for model support.
Supported Languages 
English (native), Chinese (limited)
Training Details 
Data Sources:
2GB English dataset, 5GB English-Chinese dataset, Medical COT, Action packed character play
Data Volume:
7GB total (including both datasets)
Methodology:
Annotation by 20 postdocs using strict COT and BERT judges for embeddings
Model Architecture:
Based on llama3
Input Output 
Input Format:
<|begin_of_text|><|start_header_id|>...
Output Format:
<|eot_id|>
Release Notes 
Version:
8b
Notes:
Direct upgrade over cat 70B, 2x dataset size, added Chinese support. Based on llama3.
LLM NameLlama3 Turbcat Instruct 8B Bpw2.5 EXL2
Repository ๐Ÿค—https://huggingface.co/blockblockblock/llama3-turbcat-instruct-8b-bpw2.5-exl2 
Model Size8b
Required VRAM3.6 GB
Updated2025-06-01
Maintainerblockblockblock
Model Typellama
Instruction-BasedYes
Model Files  3.6 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama3 Turbcat Instruct 8B Bpw2.5 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB112
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB111
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB92
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB110
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB7125
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB4517
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB231
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB103
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB201
...B Instruct 262k V2 EXL2 8.0bpw256K / 8.4 GB180
Note: green Score (e.g. "73.2") means that the model is better than blockblockblock/llama3-turbcat-instruct-8b-bpw2.5-exl2.

Rank the Llama3 Turbcat Instruct 8B Bpw2.5 EXL2 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? 47770 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227