Yi 1.5 34B by 01-ai

 ยป  All LLMs  ยป  01-ai  ยป  Yi 1.5 34B   URL Share it on

  Arxiv:2403.04652   Autotrain compatible   Endpoints compatible   Ggml   Gguf   License:apache-2.0   Llama   Q4   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Yi 1.5 34B 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  
Yi 1.5 34B (01-ai/Yi-1.5-34B)

Quantized Models of the Yi 1.5 34B

Model
Likes
Downloads
VRAM
....9.1 Yi 1.5 34B 5.0bpw H6 EXL22222 GB
....9.1 Yi 1.5 34B 8.0bpw H8 EXL201132 GB

Best Alternatives to Yi 1.5 34B

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
SUS Chat 34B85.038K / 68.9 GB4884116
Yi 34B79.534K / 68.9 GB114571256
SUS Chat 34B GPTQ74.68K / 18.6 GB23
SUS Chat 34B AWQ74.68K / 19.3 GB429
...Hermes 2 Yi 34B 3.0bpw H6 EXL269.74K / 13.9 GB32
...Hermes 2 Yi 34B 4.0bpw H6 EXL269.74K / 18.1 GB44
...ermes 2 Yi 34B 4.65bpw H6 EXL269.74K / 20.7 GB41
...Hermes 2 Yi 34B 5.0bpw H6 EXL269.74K / 22.2 GB41
Yi 1.5 34B Chat Bpw2.25 EXL24K / 10.7 GB330
Yi 1.5 34B Chat Bpw2.5 EXL24K / 11.8 GB170
Note: green Score (e.g. "73.2") means that the model is better than 01-ai/Yi-1.5-34B.

Yi 1.5 34B Parameters and Internals

LLM NameYi 1.5 34B
RepositoryOpen on ๐Ÿค— 
Model Size34b
Required VRAM69.2 GB
Updated2024-05-22
Maintainer01-ai
Model Typellama
Model Files  20.7 GB   4.8 GB: 1-of-15   4.8 GB: 2-of-15   5.0 GB: 3-of-15   4.8 GB: 4-of-15   4.8 GB: 5-of-15   5.0 GB: 6-of-15   4.8 GB: 7-of-15   4.8 GB: 8-of-15   5.0 GB: 9-of-15   4.8 GB: 10-of-15   4.8 GB: 11-of-15   5.0 GB: 12-of-15   4.8 GB: 13-of-15   4.8 GB: 14-of-15   1.2 GB: 15-of-15
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|q4|gguf|q4_k
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 35549 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801