LWM Text Chat 512K 5.0bpw H6 EXL2 by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  LWM Text Chat 512K 5.0bpw H6 EXL2   URL Share it on

  Autotrain compatible   Exl2   Llama   Pytorch   Quantized   Region:us

LWM Text Chat 512K 5.0bpw H6 EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LWM Text Chat 512K 5.0bpw H6 EXL2 (LoneStriker/LWM-Text-Chat-512K-5.0bpw-h6-exl2)

LWM Text Chat 512K 5.0bpw H6 EXL2 Parameters and Internals

Model Type 
auto-regressive, transformer architecture
Training Details 
Data Sources:
Books3
Data Volume:
3500 subset of Books3 documents with 500K to 1M tokens
LLM NameLWM Text Chat 512K 5.0bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/LoneStriker/LWM-Text-Chat-512K-5.0bpw-h6-exl2 
Required VRAM4.4 GB
Updated2024-12-22
MaintainerLoneStriker
Model Typellama
Model Files  4.4 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length524288
Model Max Length524288
Transformers Version4.29.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to LWM Text Chat 512K 5.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
... Text Chat 512K 6.0bpw H6 EXL2512K / 5.2 GB71
Phi 3.5 Instruct Vul128K / 7.6 GB120
...ene Phi 3.5 Mini Instruct Orpo128K / 7.6 GB91
... Text Chat 128K 6.0bpw H6 EXL2128K / 5.2 GB91
QuantumQuill16K / 2.2 GB190
CodeMate V0.1 6.0bpw H6 EXL216K / 25.7 GB121
...oros C34b 3.1.2 8.0bpw H6 EXL216K / 34 GB201
TinyLlama QuantumQuill Chat15K / 2.2 GB210
Llama3 Prime EXL2 4bpw8K / 5 GB70
Jenna V34K / 2.2 GB130
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/LWM-Text-Chat-512K-5.0bpw-h6-exl2.

Rank the LWM Text Chat 512K 5.0bpw H6 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? 40066 in total.

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