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

Rubra 11B H 5.0bpw EXL2 by sanjay920

 »  All LLMs  »  sanjay920  »  Rubra 11B H 5.0bpw EXL2   URL Share it on

  18   
  Autoquant   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational   Endpoints compatible   Exl2   Freeze   Generated from trainer   Instruct   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/sanjay920/rubra-11b-h-5.0bpw-exl2 

Rubra 11B H 5.0bpw EXL2 Benchmarks

LLME Score: 0.1885
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rubra 11B H 5.0bpw EXL2 (sanjay920/rubra-11b-h-5.0bpw-exl2)

Rubra 11B H 5.0bpw EXL2 Parameters and Internals

Model Type 
code generation, conversational AI
Use Cases 
Areas:
Research, Commercial applications
Applications:
Multi-turn chat capabilities, General conversation
Primary Use Cases:
Code assistance, Conversational AI
Limitations:
Not aligned for safety, May produce biased generations
Additional Notes 
Due to being under development, biases and safety alignment are still being worked on.
Training Details 
Methodology:
Fine-tuning to retain and enhance reasoning abilities while avoiding destructive forgetting.
Context Length:
32000
Input Output 
Input Format:
Prompts should be surrounded by [INST] and [/INST] tokens.
Accepted Modalities:
text
Output Format:
Text-based responses
Release Notes 
Version:
v0.1
Notes:
Initial release with emphasis on preserving instruct model capabilities with added reasoning.
LLM NameRubra 11B H 5.0bpw EXL2
Repository 🤗https://huggingface.co/sanjay920/rubra-11b-h-5.0bpw-exl2 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.2
Model Size7b
Required VRAM1.7 GB
Updated2024-12-21
Maintainersanjay920
Model Typemistral
Instruction-BasedYes
Model Files  0.0 GB   1.7 GB   6.9 GB
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Rubra 11B H 5.0bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...al Nemo Instruct 2407 Bnb 4bit1000K / 8.3 GB1876825
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB24123215
NaturalLM 7B Instruct32K / 14.5 GB7810
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB6347513
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB6401
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB80
...eMistral 7B Instruct Ead 16bit32K / 14.5 GB380
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1229631
Mistral 7B Instruct V0.2 8bit32K / 7.6 GB221
Mistral Turkish V232K / 14.4 GB31426
Note: green Score (e.g. "73.2") means that the model is better than sanjay920/rubra-11b-h-5.0bpw-exl2.

Rank the Rubra 11B H 5.0bpw 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? 40013 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