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

CausalLM 14B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  CausalLM 14B AWQ   URL Share it on

  41   
  4-bit   Autotrain compatible   Awq   Base model:causallm/14b Base model:quantized:causallm/...   Dataset:baai/coig   Dataset:fnlp/moss-003-sft-data Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-3.... Dataset:josephuscheung/guanaco...   Dataset:ldjnr/puffin Dataset:liuhaotian/llava-instr...   Dataset:liwu/mnbvc   Dataset:meta-math/metamathqa Dataset:milashkaarshif/moegirl...   Dataset:open-orca/openorca   Dataset:openbmb/llava zh   Dataset:ryokoai/fandom23k   Dataset:ryokoai/sharegpt52k   Dataset:stingning/ultrachat   Dataset:teknium/openhermes Dataset:tigerresearch/tigerbot...   Dataset:wiki lingua   Dataset:wikipedia Dataset:wizardlm/wizardlm evol...   En   Instruct   Llama   Llama2   Quantized   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/TheBloke/CausalLM-14B-AWQ 

CausalLM 14B AWQ Benchmarks

LLME Score: 0.149
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CausalLM 14B AWQ (TheBloke/CausalLM-14B-AWQ)

CausalLM 14B AWQ Parameters and Internals

Model Type 
llama, text-generation
Use Cases 
Areas:
text generation, multimodal capabilities
Applications:
research, multimodal implementation
Primary Use Cases:
Chat and conversational AI using system-user-assistant prompts
Limitations:
Potential hallucinations or unreliable outputs, Presence of objectionable content
Considerations:
Complete safety checks and filter output keywords for offensive content
Additional Notes 
Model quantization using AWQ for improved speed and storage efficiency. Uses prompt templates similar to LLaVA1.5 for visual instructions. Can utilize AutoAWQ for Python compatibility and GPU inference.
Supported Languages 
en (full proficiency), zh (full proficiency)
Training Details 
Data Sources:
JosephusCheung/GuanacoDataset, Open-Orca/OpenOrca, stingning/ultrachat, meta-math/MetaMathQA, liuhaotian/LLaVA-Instruct-150K, jondurbin/airoboros-3.1, WizardLM/WizardLM_evol_instruct_V2_196k, RyokoAI/ShareGPT52K, RyokoAI/Fandom23K, milashkaarshif/MoeGirlPedia_wikitext_raw_archive, wikipedia, wiki_lingua, fnlp/moss-003-sft-data, garage-bAInd/Open-Platypus, LDJnr/Puffin, openbmb/llava_zh, BAAI/COIG, TigerResearch/tigerbot-zhihu-zh-10k, liwu/MNBVC, teknium/openhermes
Data Volume:
1.3B tokens
Methodology:
Dataset curation and synthetic data augmentation from open source datasets
Model Architecture:
Identical to LLaMA2
Safety Evaluation 
Ethical Considerations:
Trained on unfiltered internet data; potential for objectionable content
Input Output 
Input Format:
ChatML system-user-assistant prompt format
Accepted Modalities:
text
Output Format:
text
LLM NameCausalLM 14B AWQ
Repository 🤗https://huggingface.co/TheBloke/CausalLM-14B-AWQ 
Model NameCausalLM 14B
Model CreatorCausalLM
Base Model(s)  14B   CausalLM/14B
Model Size14b
Required VRAM9.7 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  9.7 GB
Supported Languagesen zh
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensewtfpl
Context Length8192
Model Max Length8192
Transformers Version4.34.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size152064
Torch Data Typefloat16

Best Alternatives to CausalLM 14B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CausalLM 14B EXL28K / 8.5 GB703
14B8K / 28.4 GB1942297
CausalLM 14B GPTQ8K / 9.7 GB3820
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CausalLM-14B-AWQ.

Rank the CausalLM 14B AWQ 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? 40066 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