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

SILMA 9B Instruct V1.0 by silma-ai

 »  All LLMs  »  silma-ai  »  SILMA 9B Instruct V1.0   URL Share it on

  11047   
  Ar   Autotrain compatible   Conversational   En   Endpoints compatible   Gemma2   Instruct   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/silma-ai/SILMA-9B-Instruct-v1.0 

SILMA 9B Instruct V1.0 Benchmarks

MMLU Pro: 32.44
GPQA: 7.38
MUSR: 17.26
BBH: 30.71
IFEval: 58.42 vs 88 (so35)-33.6%
LLME Score: 0.37692
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SILMA 9B Instruct V1.0 (silma-ai/SILMA-9B-Instruct-v1.0)

SILMA 9B Instruct V1.0 Parameters and Internals

Model Type 
text generation, conversational
Use Cases 
Areas:
Content Creation and Communication, Research and Education
Applications:
Text Generation, Chatbots and Conversational AI, Text Summarization
Additional Notes 
The model can be run up to 6x faster using torch compile features.
Supported Languages 
Arabic (native), English (native)
Responsible Ai Considerations 
Fairness:
LLMs trained on large-scale, real-world text data can reflect socio-cultural biases embedded in the training material.
Transparency:
This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.
Accountability:
Guidelines are provided for responsible use with the model.
Mitigation Strategies:
Mechanisms and guidelines for content safety are essential. Developers are encouraged to exercise caution and implement appropriate content safety safeguards.
Input Output 
Input Format:
Text string, such as a question, a prompt, or a document to be summarized.
Accepted Modalities:
text
Output Format:
Generated Arabic or English text in response.
Release Notes 
Version:
SILMA-9B-Instruct-v1.0
Notes:
Initial model release with open-weight access for deployment across various use-cases
LLM NameSILMA 9B Instruct V1.0
Repository 🤗https://huggingface.co/silma-ai/SILMA-9B-Instruct-v1.0 
Model Size9b
Required VRAM18.6 GB
Updated2024-12-22
Maintainersilma-ai
Model Typegemma2
Instruction-BasedYes
Model Files  3.9 GB: 1-of-5   4.0 GB: 2-of-5   4.0 GB: 3-of-5   4.0 GB: 4-of-5   2.7 GB: 5-of-5
Supported Languagesar en
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.43.4
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to SILMA 9B Instruct V1.0

Best Alternatives
Context / RAM
Downloads
Likes
...2 9B Cpt Sahabatai V1 Instruct8K / 18.6 GB347627
Gemma Evo 10B8K / 20.4 GB241
Odin 9B8K / 18.6 GB26674
...B IT Simpo Infinity Preference8K / 18.6 GB266215
...ma2 9B Cpt Sea Lionv3 Instruct8K / 18.6 GB59935
SahabatAI Lion 9B TIES V18K / 18.6 GB1371
FuseChat Gemma 2 9B Instruct8K / 18.6 GB753
Gemma 2 9B MOTH8K / 37.1 GB330
RoGemma2 9B Instruct8K / 18.6 GB120
Gemma 2 9B Instruct 4Bit GPTQ8K / 6.2 GB1833
Note: green Score (e.g. "73.2") means that the model is better than silma-ai/SILMA-9B-Instruct-v1.0.

Rank the SILMA 9B Instruct V1.0 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? 40066 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