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

Shiftdocs 7B Ocp4.15 V0.3 by boricua

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

  13   

Shiftdocs 7B Ocp4.15 V0.3 is an open-source language model by boricua. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

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

Shiftdocs 7B Ocp4.15 V0.3 Benchmarks

LLME Score: 0.13353
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Shiftdocs 7B Ocp4.15 V0.3 (boricua/shiftdocs-7b-ocp4.15-v0.3)
🌟 Advertise your project 🚀

Shiftdocs 7B Ocp4.15 V0.3 Parameters and Internals

Model Type 
Q&A, Instruction Following
Use Cases 
Areas:
proof of concept, Kubernetes-related tasks
Primary Use Cases:
Answering questions related to OpenShift and Kubernetes
Limitations:
Significant drop in accuracy and performance when quantized., Refuses valid Kubernetes or OpenShift questions if unrelated context present during training.
Considerations:
Not intended for production use; trained in lab environment.
Supported Languages 
en (advanced)
Training Details 
Data Sources:
OpenShift 4.15 documentation
Data Volume:
45212 Q&A pairs
Methodology:
The Q&A corpus was generated from OpenShift 4.15 PDFs, with questions generated by Mistral-7B-Instruct-v0.2 and answers by Mixtral-8x22B-Instruct-v0.1. A voting evaluation with Llama3-7B was used to ensure quality, excluding pairs focusing on phrases like 'this example'.
Context Length:
32000
Training Time:
3000 iterations
Responsible Ai Considerations 
Mitigation Strategies:
Trained to refuse non-Kubernetes-related questions, but may still misinterpret or fabricate if context is absent.
Input Output 
Input Format:
INSTRUCTIONS, TASK, CONTEXT, QUESTION
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use RAG to enhance model's knowledge.
LLM NameShiftdocs 7B Ocp4.15 V0.3
Repository 🤗https://huggingface.co/boricua/shiftdocs-7b-ocp4.15-v0.3 
Model Size7b
Required VRAM14.5 GB
Updated2025-12-10
Maintainerboricua
Model Typemistral
Model Files  14.5 GB   14.5 GB
Supported Languagesen
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Padding Token<|pad|>
Vocabulary Size32008
Torch Data Typebfloat16

Best Alternatives to Shiftdocs 7B Ocp4.15 V0.3

Best Alternatives
Context / RAM
Downloads
Likes
Mistrilitary 7B32K / 7.7 GB9922
Mistral Scary Story Finetune32K / 14.5 GB410
Mistral 7B V0.2 Csn SFT32K / 14.4 GB50
Instruct 16bit32K / 0.4 GB50
BioMistral 7B GGUF32K / 1 GB108519
Merlinite 7B Ocp4.15 V0.332K / 14.5 GB50
AzzurroQuantized32K / 4.4 GB3334
Merlinite 7B Ocp4.15 V0.132K / 4.4 GB80
Filiberto 7B Instruct Exp132K / 14.5 GB190
MistralMusic32K / 14.4 GB151
Note: green Score (e.g. "73.2") means that the model is better than boricua/shiftdocs-7b-ocp4.15-v0.3.

Rank the Shiftdocs 7B 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer