Tulu 2 DPO 7B by allenai

 ยป  All LLMs  ยป  allenai  ยป  Tulu 2 DPO 7B   URL Share it on

  Arxiv:2305.18290   Arxiv:2311.10702   Autotrain compatible Base model:meta-llama/llama-2-...   Conversational Dataset:allenai/tulu-v2-sft-mi... Dataset:huggingfaceh4/ultrafee...   En   Endpoints compatible   License:other   Llama   Pytorch   Region:us   Sharded

Rank the Tulu 2 DPO 7B 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  
Tulu 2 DPO 7B (allenai/tulu-2-dpo-7b)

Quantized Models of the Tulu 2 DPO 7B

Tulu 2 DPO 7B GGUF31822 GB
Tulu 2 DPO 7B GPTQ07693 GB
Tulu 2 DPO 7B AWQ0193 GB

Best Alternatives to Tulu 2 DPO 7B

Best Alternatives
HF Rank
Vicuna 7B V1.555.274K / 13.5 GB711532237
Llama2 Chinese 7B Chat54.234K / 13.5 GB7153211
Vicuna 7B V1.5 16K54.024K / 13.5 GB3983183
Deepseek Llm 7B Base52.334K / 13.9 GB362629
Deepseek Llm 7B Chat49.554K / 13.9 GB869565
Vicuna 7B V1.5 GPTQ48.54K / 3.9 GB144615
Vicuna 7B V1.5 AWQ48.54K / 3.9 GB1283
Vicuna 7B V1.5 16K GPTQ47.44K / 3.9 GB3818010
Vicuna 7B V1.5 16K AWQ47.44K / 3.9 GB411
Vicuna 7B V1.5 16K Gptq47.44K / 3.9 GB150
Note: green Score (e.g. "73.2") means that the model is better than allenai/tulu-2-dpo-7b.

Tulu 2 DPO 7B Parameters and Internals

LLM NameTulu 2 DPO 7B
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Llama 2 7B Hf   meta-llama/Llama-2-7b-hf
Model Size7b
Required VRAM13.5 GB
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.33.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34817 in total.

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