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

Open Instruct Human Mix 65B by allenai

 »  All LLMs  »  allenai  »  Open Instruct Human Mix 65B   URL Share it on

  1378   
  Arxiv:2301.13688   Arxiv:2302.13971   Arxiv:2304.07327   Arxiv:2306.04751   Autotrain compatible Dataset:databricks/databricks-...   Dataset:openassistant/oasst1   En   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/allenai/open-instruct-human-mix-65b 

Open Instruct Human Mix 65B Benchmarks

LLME Score: 0.12537
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Open Instruct Human Mix 65B (allenai/open-instruct-human-mix-65b)

Open Instruct Human Mix 65B Parameters and Internals

Model Type 
instruction-tuned
Additional Notes 
To use the model, requires conversion of LLaMa model to HF format and use of weight_diff script.
Training Details 
Data Sources:
databricks/databricks-dolly-15k, OpenAssistant/oasst1
Input Output 
Input Format:
<|user|> Your message here! <|assistant|>
Performance Tips:
Include a newline after '<|assistant|>' for improved generation quality.
LLM NameOpen Instruct Human Mix 65B
Repository 🤗https://huggingface.co/allenai/open-instruct-human-mix-65b 
Model Size65b
Required VRAM260.8 GB
Updated2025-02-05
Maintainerallenai
Model Typellama
Instruction-BasedYes
Model Files  9.3 GB: 1-of-27   9.7 GB: 2-of-27   9.7 GB: 3-of-27   9.7 GB: 4-of-27   9.7 GB: 5-of-27   9.7 GB: 6-of-27   9.7 GB: 7-of-27   9.7 GB: 8-of-27   9.7 GB: 9-of-27   9.7 GB: 10-of-27   9.7 GB: 11-of-27   9.7 GB: 12-of-27   9.7 GB: 13-of-27   9.7 GB: 14-of-27   9.7 GB: 15-of-27   9.7 GB: 16-of-27   9.7 GB: 17-of-27   9.7 GB: 18-of-27   9.7 GB: 19-of-27   9.7 GB: 20-of-27   9.7 GB: 21-of-27   9.7 GB: 22-of-27   9.7 GB: 23-of-27   9.7 GB: 24-of-27   9.7 GB: 25-of-27   9.7 GB: 26-of-27   9.0 GB: 27-of-27
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.29.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32001
Torch Data Typefloat32

Quantized Models of the Open Instruct Human Mix 65B

Model
Likes
Downloads
VRAM
...en Instruct Human Mix 65B GGUF16327 GB
...en Instruct Human Mix 65B GPTQ01933 GB
...pen Instruct Human Mix 65B AWQ0834 GB

Best Alternatives to Open Instruct Human Mix 65B

Best Alternatives
Context / RAM
Downloads
Likes
Lite Oute 1 65M Instruct2K / 0.3 GB1511
Llama 65B Instruct2K / 130.4 GB130214
Open Instruct Sharegpt 65B2K / 260.8 GB202
...en Instruct Human Mix 65B GPTQ2K / 33.5 GB190
...pen Instruct Human Mix 65B AWQ2K / 34.7 GB80
...pstage Llama1 65B Instruct AWQ2K / 34.7 GB81
...stage Llama1 65B Instruct GPTQ2K / 34.7 GB123
Note: green Score (e.g. "73.2") means that the model is better than allenai/open-instruct-human-mix-65b.

Rank the Open Instruct Human Mix 65B 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? 42577 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 v20241227
  Support LLM Explorer