AmberChat GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  AmberChat GPTQ   URL Share it on

  4-bit   Autotrain compatible   Base model:llm360/amberchat Base model:quantized:llm360/am... Dataset:icybee/share gpt 90k v... Dataset:wizardlm/wizardlm evol...   En   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/TheBloke/AmberChat-GPTQ 

AmberChat GPTQ Benchmarks

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

AmberChat GPTQ Parameters and Internals

Model Type 
Language model with the same architecture as LLaMA-7B
Additional Notes 
Model includes quantization options provided by TheBloke.
Supported Languages 
English (NLP)
Training Details 
Data Sources:
WizardLM/WizardLM_evol_instruct_V2_196k, icybee/share_gpt_90k_v1
Data Volume:
Total: 233k rows
Context Length:
2048
Input Output 
Input Format:
A chat prompt with format: 'USER: {prompt} ASSISTANT: '
Accepted Modalities:
text
Output Format:
text generation
LLM NameAmberChat GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/AmberChat-GPTQ 
Model NameAmberChat
Model CreatorLLM360
Base Model(s)  AmberChat   LLM360/AmberChat
Model Size1.1b
Required VRAM3.9 GB
Updated2024-12-23
MaintainerTheBloke
Model Typeamber
Instruction-BasedYes
Model Files  3.9 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to AmberChat GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Law Chat GPTQ4K / 3.9 GB474
Medicine Chat GPTQ4K / 3.9 GB346
Finance Chat GPTQ4K / 3.9 GB183
...1B 32K Instruct 8.0bpw H8 EXL232K / 1.2 GB51
...1B 32K Instruct 3.0bpw H6 EXL232K / 0.5 GB60
...nish English Asistant 16bit V22K / 2.2 GB130
TinyLlama 1.1B 32K Instruct32K / 2.2 GB55212
...llama 1.1B 16K Instructions V432K / 2.2 GB140
Palmer 002 32K32K / 2.2 GB210
...lama 1.1B 16K Instructions Rag32K / 2.2 GB220
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/AmberChat-GPTQ.

Rank the AmberChat GPTQ 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? 40126 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217