Chatbloom 1b7 Sft by nicholascao

 ยป  All LLMs  ยป  nicholascao  ยป  Chatbloom 1b7 Sft   URL Share it on

  Autotrain compatible   Bloom   Chat Dataset:bellegroup/multiturn c...   Dataset:bellegroup/train 1m cn Dataset:jeffwan/sharegpt vicun...   En   Endpoints compatible   Fp16   Ggml   Pytorch   Q4   Quantized   Region:us   Safetensors   Zh

Chatbloom 1b7 Sft Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chatbloom 1b7 Sft (nicholascao/chatbloom-1b7-sft)

Chatbloom 1b7 Sft Parameters and Internals

Model Type 
text-generation, bilingual dialogue model
Use Cases 
Areas:
research
Applications:
dialogue systems, chatbot applications
Limitations:
Commercial and other potentially harmful uses are not allowed.
Additional Notes 
This model supports Chinese and English and is a bilingual dialogue model.
Supported Languages 
zh (Chinese), en (English)
Training Details 
Data Sources:
BelleGroup/train_1M_CN, BelleGroup/multiturn_chat_0.8M, jeffwan/sharegpt_vicuna
Methodology:
SFT (Supervised Fine-Tuning)
Input Output 
Input Format:
tokenized format as per transformer models
Accepted Modalities:
text
Output Format:
text
LLM NameChatbloom 1b7 Sft
Repository ๐Ÿค—https://huggingface.co/nicholascao/chatbloom-1b7-sft 
Model Size1m
Required VRAM1.4 GB
Updated2025-02-22
Maintainernicholascao
Model Typebloom
Model Files  1.4 GB   3.4 GB   3.4 GB
Supported Languageszh en
GGML QuantizationYes
Quantization Typefp16|ggml|q4
Model ArchitectureBloomForCausalLM
Transformers Version4.29.0.dev0
Tokenizer ClassBloomTokenizer
Padding Token<pad>
Vocabulary Size250682
Torch Data Typefloat16

Best Alternatives to Chatbloom 1b7 Sft

Best Alternatives
Context / RAM
Downloads
Likes
FlorRAG 4bit0K / 3.6 GB120
Bloom 1b Quantized0K / 1.4 GB19750
Bloom 7b1 Petals0K / 2.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than nicholascao/chatbloom-1b7-sft.

Rank the Chatbloom 1b7 Sft 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227