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

Breeze 7B PTT Chat V2 by Riyuechang

 »  All LLMs  »  Riyuechang  »  Breeze 7B PTT Chat V2   URL Share it on

  6   
Base model:finetune:mediatek-r... Base model:mediatek-research/b...   Conversational Dataset:riyuechang/ptt-corpus-...   Instruct   Mistral   Ptt   Ptt chat   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Riyuechang/Breeze-7B-PTT-Chat-v2 

Breeze 7B PTT Chat V2 Benchmarks

LLME Score: 0.21765
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Breeze 7B PTT Chat V2 (Riyuechang/Breeze-7B-PTT-Chat-v2)

Breeze 7B PTT Chat V2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model fine-tuned using LoRa with specific parameters and training regime. Achieved a training loss of 0.9391.
Training Details 
Data Sources:
Riyuechang/PTT-Corpus-100K_Gossiping-1400-39400_v2
Methodology:
Filtered from large data to remove noise.
Hardware Used:
NVIDIA GeForce RTX 3060 12G
Release Notes 
Version:
1.0
Notes:
使用新的噪聲較小(理論上)的數據訓練 Lora使用了更大的r(32) 取消了Dora 因為Dora的提升有限，還會大幅降低訓練和推理的效率
LLM NameBreeze 7B PTT Chat V2
Repository 🤗https://huggingface.co/Riyuechang/Breeze-7B-PTT-Chat-v2 
Base Model(s)  Breeze 7B Instruct V1.0   MediaTek-Research/Breeze-7B-Instruct-v1_0
Model Size7b
Required VRAM15 GB
Updated2025-02-05
MaintainerRiyuechang
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.6 GB: 3-of-4   0.5 GB: 4-of-4
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size61952
Torch Data Typebfloat16

Best Alternatives to Breeze 7B PTT Chat V2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB760
...1 Summarize 64K LoRANET Merged128K / 14.4 GB50
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB12462781551
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37145
...ty Instruct 3M 0613 Mistral 7B32K / 14.4 GB641511
Note: green Score (e.g. "73.2") means that the model is better than Riyuechang/Breeze-7B-PTT-Chat-v2.

Rank the Breeze 7B PTT Chat V2 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? 42577 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