Tulu 2 70B 6.0bpw H6 EXL2 by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Tulu 2 70B 6.0bpw H6 EXL2   URL Share it on

  Arxiv:2311.10702   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-2-... Dataset:allenai/tulu-v2-sft-mi...   En   Endpoints compatible   Exl2   Llama   Pytorch   Quantized   Region:us   Sharded   Tensorflow

Tulu 2 70B 6.0bpw 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").
Tulu 2 70B 6.0bpw H6 EXL2 (LoneStriker/tulu-2-70b-6.0bpw-h6-exl2)

Tulu 2 70B 6.0bpw H6 EXL2 Parameters and Internals

Model Type 
Instruction-tuned, RLHF-tuned, Chat model
Use Cases 
Areas:
Research, Assistant applications
Applications:
Chatbots, Virtual assistants
Primary Use Cases:
Assistive chat applications
Supported Languages 
en (Primary)
Training Details 
Data Sources:
Publicly available datasets, Synthetic datasets, Human-created datasets
Methodology:
Fine-tuned version of Llama 2 with instruction and RLHF tuning
Input Output 
Input Format:
<|user|> Your message here! <|assistant|>
Accepted Modalities:
text
Output Format:
Text completions
Performance Tips:
Include a newline after <|assistant|> for better generation quality.
LLM NameTulu 2 70B 6.0bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/LoneStriker/tulu-2-70b-6.0bpw-h6-exl2 
Base Model(s)  Llama 2 70B Hf   meta-llama/Llama-2-70b-hf
Model Size70b
Required VRAM52.2 GB
Updated2024-12-23
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-7   8.5 GB: 2-of-7   8.5 GB: 3-of-7   8.6 GB: 4-of-7   8.5 GB: 5-of-7   8.6 GB: 6-of-7   0.9 GB: 7-of-7
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Tulu 2 70B 6.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB155
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB183
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB122
...0B Instruct Gradient 262K 4bit256K / 39.7 GB163
...0B Instruct Gradient 262K 8bit256K / 75 GB82
...0B Instruct Gradient 262K 2bit256K / 21.9 GB151
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB161
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB120
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/tulu-2-70b-6.0bpw-h6-exl2.

Rank the Tulu 2 70B 6.0bpw 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? 40123 in total.

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