Mistral Sharegpt90k by pacozaa

 ยป  All LLMs  ยป  pacozaa  ยป  Mistral Sharegpt90k   URL Share it on

  4bit Base model:finetune:unsloth/mi... Base model:unsloth/mistral-7b-...   Dataset:liyucheng/sharegpt90k   En   Endpoints compatible   Lora   Lora adapter   Mistral   Ollama   Peft   Quantized   Region:us   Safetensors   Tensorboard   Trl   Unsloth

Mistral Sharegpt90k Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Mistral Sharegpt90k Parameters and Internals

Model Type 
text-generation-inference, LoRA Adapter
Additional Notes 
The training step is increasing over time, currently at 550 steps during fine-tuning in Colab.
Supported Languages 
en (high)
Training Details 
Data Sources:
liyucheng/ShareGPT90K
Methodology:
Fine-tuning using LoRA Adapter
Model Architecture:
Mistral model with LoRA Adapter
LLM NameMistral Sharegpt90k
Repository ๐Ÿค—https://huggingface.co/pacozaa/mistral-sharegpt90k 
Base Model(s)  Mistral 7B Bnb 4bit   unsloth/mistral-7b-bnb-4bit
Model Size7b
Required VRAM0.2 GB
Updated2024-11-21
Maintainerpacozaa
Model Files  0.2 GB   0.0 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureAutoModel
Licenseapache-2.0
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|down_proj|q_proj|gate_proj|v_proj|k_proj|up_proj
LoRA Alpha16
LoRA Dropout0
R Param16
Mistral Sharegpt90k (pacozaa/mistral-sharegpt90k)

Best Alternatives to Mistral Sharegpt90k

Best Alternatives
Context / RAM
Downloads
Likes
Qwen 2.1 7B Persona Lora Model0K / 0.2 GB01
Qwen2.5 7B Exp2 Lora Model0K / 0.2 GB01
Qwen 2.5 7B Rp Lora0K / 0.2 GB01
Text Completion0K / 2.4 GB01
Cognitive Hacker0.20K / 0.2 GB01
Cognitive Hacker0K / 0.2 GB01
Lora Model0K / 0.2 GB01
Mistral 7B Bnb 4bit Lora Model0K / 0.2 GB01
Swahili Gemma Lora0K / 0.2 GB02
Gemma Swahili Mollel 1 Epoch0K / 0.2 GB02
Note: green Score (e.g. "73.2") means that the model is better than pacozaa/mistral-sharegpt90k.

Rank the Mistral Sharegpt90k 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? 38199 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110