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

34B Beta 4.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  34B Beta 4.0bpw H6 EXL2   URL Share it on

  6   
  Autotrain compatible   Conversational   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/34b-beta-4.0bpw-h6-exl2 

34B Beta 4.0bpw H6 EXL2 Benchmarks

LLME Score: 0.17561
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
34B Beta 4.0bpw H6 EXL2 (LoneStriker/34b-beta-4.0bpw-h6-exl2)

34B Beta 4.0bpw H6 EXL2 Parameters and Internals

Model Type 
Causal Language Model
Use Cases 
Considerations:
Avoid using "accelerated inference frameworks" like VLLM due to precision issues leading to significant output quality degradation. Use Transformers for inference, or consider using q8_0 quantization with llama.cpp temporarily for faster inference.
Additional Notes 
Some issues with model weights in terms of precision, to be fixed in the next version update. Repetition penalty should not be used. Re-alignment on synthetic datasets has changed distribution significantly from original datasets.
LLM Name34B Beta 4.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/34b-beta-4.0bpw-h6-exl2 
Model Size34b
Required VRAM18.1 GB
Updated2024-12-22
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   0.9 GB: 3-of-3
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensegpl-3.0
Context Length200000
Model Max Length200000
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to 34B Beta 4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Yi 34B 200K RPMerge195K / 68.9 GB48760
...34B 200K Aezakmi Raw 1902 EXL2195K / 20.7 GB101
Yi 34B 200K MAR2024 EXL2 4bpw195K / 18 GB91
...B 200K RPMerge 4.65bpw H6 EXL2195K / 10.5 GB121
...mi Raw Toxic 2702 4.65bpw EXL2195K / 20.8 GB72
Yi 34B 200K RPMerge EXL2 40bpw195K / 18.1 GB3420
Opus V1 34B 5.0bpw H6 EXL2195K / 22.3 GB72
Opus V1 34B 8.0bpw H8 EXL2195K / 34.8 GB101
Opus V1 34B 4.0bpw H6 EXL2195K / 18 GB51
34B Beta 5.0bpw H6 EXL2195K / 22.3 GB91
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/34b-beta-4.0bpw-h6-exl2.

Rank the 34B Beta 4.0bpw H6 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? 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