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

Granite 7B Lab Ocp4.15 V0.3 by boricua

 »  All LLMs  »  boricua  »  Granite 7B Lab Ocp4.15 V0.3   URL Share it on

  13   
  Autotrain compatible   Conversational   En   Endpoints compatible   F16   Ggml   Gguf   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/boricua/granite-7b-lab-ocp4.15-v0.3 

Granite 7B Lab Ocp4.15 V0.3 Benchmarks

LLME Score: 0.18506
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Granite 7B Lab Ocp4.15 V0.3 (boricua/granite-7b-lab-ocp4.15-v0.3)

Granite 7B Lab Ocp4.15 V0.3 Parameters and Internals

Model Type 
Q&A model
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
fine tuning a base model with expertise and basic guardrails, improving response quality about OpenShift topics
Limitations:
not intended for production use, accuracy and performance drop in quantized version
Additional Notes 
This is a proof of concept model created in a lab environment.
Supported Languages 
en (high)
Training Details 
Data Sources:
OpenShift 4.15 documentation
Data Volume:
45212 Q&A pairs
Methodology:
Generated 5 Q&A pairs for each page on OpenShift 4.15 PDFs with lengths greater than 1500 characters using Mistral-7B-Instruct-v0.2 for questions and Mixtral-8x22B-Instruct-v0.1 for answers. A voting evaluation between Mixtral-8x22B and Llama3-7B was used to ensure quality.
Context Length:
32000
Input Output 
Input Format:
## INSTRUCTIONS ## TASK ## CONTEXT ## QUESTION
Accepted Modalities:
text
Output Format:
Q&A responses
LLM NameGranite 7B Lab Ocp4.15 V0.3
Repository 🤗https://huggingface.co/boricua/granite-7b-lab-ocp4.15-v0.3 
Model Size7b
Required VRAM13.5 GB
Updated2025-02-22
Maintainerboricua
Model Typellama
Model Files  13.5 GB   13.5 GB
Supported Languagesen
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.40.2
Padding Token<|pad|>
Vocabulary Size32008

Best Alternatives to Granite 7B Lab Ocp4.15 V0.3

Best Alternatives
Context / RAM
Downloads
Likes
Chef Ai32K / 14.4 GB220
PULI LlumiX 32K Q4 K M GGUF32K / 4.1 GB161
...lumiX 32K Instruct Q4 K M GGUF32K / 4.1 GB153
Openthaigpt 1.0.0 7B Chat4K / 13.7 GB48516
Chinese Llama 2 7B Gguf4K / 2.6 GB4164
...hat Hf Phr Mental Therapy GGUF4K / 1.5 GB100
Llama GGUF4K / 13.5 GB400
Llama2 7b Gguf Yakovlev4K / 7.2 GB170
Llama2 7B Text Sql Gguf4K / 4.1 GB90
...7B Chat Hf Function Calling V24K / 13.5 GB577132
Note: green Score (e.g. "73.2") means that the model is better than boricua/granite-7b-lab-ocp4.15-v0.3.

Rank the Granite 7B Lab Ocp4.15 V0.3 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? 43470 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