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

Tigerbot 13B Chat 4bit by TigerResearch

 »  All LLMs  »  TigerResearch  »  Tigerbot 13B Chat 4bit   URL Share it on

  20   
  4bit   Autotrain compatible   Endpoints compatible   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TigerResearch/tigerbot-13b-chat-4bit 

Tigerbot 13B Chat 4bit Benchmarks

ARC: 78.3 vs 96.7 (so35)-19%
HellaSwag: 72.4 vs 95.3 (gpt4)-24%
MMLU: 54.1 vs 88.3 (so35)-38.7%
GSM8K: 43.1 vs 96.4 (so35)-55.3%
OpenCompas: 47.7 vs 73.3 (gpt4)-34.9%
Exam: 57 vs 77.2 (gpt4)-26.2%
Language: 40 vs 62 (gpt4)-35.5%
Knowledge: 50.9 vs 73.5 (gpt4)-30.7%
Understand: 60.2 vs 70 (gpt4)-14%
Reasoning: 41.8 vs 74.4 (gpt4)-43.8%
LLME Score: 0.13339
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tigerbot 13B Chat 4bit (TigerResearch/tigerbot-13b-chat-4bit)

Tigerbot 13B Chat 4bit Parameters and Internals

Model Type 
text generation
Additional Notes 
4-bit version quantized using GPTQ.
LLM NameTigerbot 13B Chat 4bit
Repository 🤗https://huggingface.co/TigerResearch/tigerbot-13b-chat-4bit 
Base Model(s)  Tigerbot 13B Chat V2   TigerResearch/tigerbot-13b-chat-v2
Model Size13b
Required VRAM9.1 GB
Updated2024-12-26
MaintainerTigerResearch
Model Typellama
Model Files  9.1 GB
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size60928
Torch Data Typefloat32

Best Alternatives to Tigerbot 13B Chat 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Llama13b 32K Illumeet Finetune32K / 26 GB280
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB211
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB191
WhiteRabbitNeo 13B V116K / 26 GB1651405
CodeLlama 13B Python Fp1616K / 26 GB147925
CodeLlama 13B Instruct Fp1616K / 26 GB193129
CodeLlama 13B Fp1616K / 26 GB1866
Codellama 13B Bnb 4bit16K / 7.2 GB911
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB572
Trinity 13B16K / 26 GB2615
Note: green Score (e.g. "73.2") means that the model is better than TigerResearch/tigerbot-13b-chat-4bit.

Rank the Tigerbot 13B Chat 4bit 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? 40248 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 v20241217
  Support LLM Explorer