ZephRP M7b AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  ZephRP M7b AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:quantized:royallab/...   Base model:royallab/zephrp-m7b   En   Mistral   Quantized   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/TheBloke/ZephRP-m7b-AWQ 

ZephRP M7b AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ZephRP M7b AWQ (TheBloke/ZephRP-m7b-AWQ)
๐ŸŒŸ Advertise your project ๐Ÿš€

ZephRP M7b AWQ Parameters and Internals

Model Type 
mistral, text-generation
Use Cases 
Areas:
roleplaying chat scenarios
Limitations:
not intended for factual information or advice
Additional Notes 
The model combines message length instruction training of LimaRPv3 with Zephyr's capabilities. It shows biases similar to niche roleplaying forums.
Supported Languages 
en (full)
Training Details 
Data Sources:
LimaRP dataset
Methodology:
merge between zephyr-7b-alpha and PEFT adapter
Hardware Used:
single L40 GPU
Model Architecture:
Mistral-7B-v0.1-based
Input Output 
Input Format:
LimaRP-Alpaca format
Accepted Modalities:
text
Output Format:
text generation
LLM NameZephRP M7b AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/ZephRP-m7b-AWQ 
Model NameZephrp m7b
Model CreatorThe Royal Lab
Base Model(s)  ZephRP M7b   royallab/ZephRP-m7b
Model Size1.2b
Required VRAM4.2 GB
Updated2025-09-11
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to ZephRP M7b AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Feedback Wizard 4bit AWQ32K / 4.2 GB60
Quantized Kheopss AWQ 4bits V132K / 4.2 GB170
Ryze AWQ 4bit32K / 4.2 GB60
...lot Engine Step Json Short AWQ32K / 4.2 GB60
...V3 Plot Chat Roleplay Chat AWQ32K / 4.2 GB60
MistralLite AWQ32K / 4.2 GB455
MistralLite AWQ32K / 4.2 GB423
SFR Embedding Mistral AWQ32K / 4.2 GB160
Dictalm2.0 Instruct AWQ32K / 4.2 GB620
LemonadeRP 4.5.3 AWQ32K / 4.2 GB50
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/ZephRP-m7b-AWQ.

Rank the ZephRP M7b AWQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51408 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124