LWM Text Chat 256K GPTQ by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  LWM Text Chat 256K GPTQ   URL Share it on

  4-bit   4bit   Autotrain compatible   Gptq   Llama   Pytorch   Quantized   Region:us

LWM Text Chat 256K GPTQ 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 256K GPTQ (LoneStriker/LWM-Text-Chat-256K-GPTQ)

LWM Text Chat 256K GPTQ Parameters and Internals

Model Type 
auto-regressive language model
Training Details 
Data Sources:
Books3
Data Volume:
37K subset with 200K to 500K tokens
Training Time:
December 2023
Model Architecture:
transformer
LLM NameLWM Text Chat 256K GPTQ
Repository ๐Ÿค—https://huggingface.co/LoneStriker/LWM-Text-Chat-256K-GPTQ 
Base Model(s)  LWM Text Chat 256K   LargeWorldModel/LWM-Text-Chat-256K
Required VRAM4.3 GB
Updated2025-02-22
MaintainerLoneStriker
Model Typellama
Model Files  4.3 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length262144
Model Max Length262144
Transformers Version4.37.2
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 256K GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text Chat 512K GPTQ512K / 4.3 GB352
LWM Text Chat 128K GPTQ128K / 4.3 GB31
StoryTeller10.7B GPTQ 4Bit41K / 6.6 GB60
Alpha Merged Gptq19K / 9.2 GB70
...lama 3 Lima Nsfw 16K Test GPTQ16K / 5.7 GB265
V3 Gptq4K / 6.1 GB50
Taiwan LLaMa V1.0 4bits GPTQ4K / 7.3 GB781
MythoMax22b Falseblock GPT4K / 12 GB50
Taiwan LLaMa V1.0 4bits GPTQ4K / 7.3 GB159
Nous Hermes Llama2 8bit GPTQ4K / 13.7 GB31
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/LWM-Text-Chat-256K-GPTQ.

Rank the LWM Text Chat 256K GPTQ 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? 43508 in total.

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