LLM EXPLORER 61,561 MODELS INDEXED

CausalLM 7B GPTQ by TheBloke

By TheBloke · 7 downloads
HF Repo ↗ Copy URL

CausalLM 7B GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 5.9GB, Context: 8K, License: wtfpl, Quantized, Instruction-Based, LLM Explorer Score: 0.09.

  4-bit   Base model:causallm/7b 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   Gptq   Instruct   Llama   Llama2   Quantized   Qwen   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/TheBloke/CausalLM-7B-GPTQ 

CausalLM 7B GPTQ Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Speculative Sampling
Applications:
Research, Text Generation
Primary Use Cases:
Multimodal Capabilities
Limitations:
May produce hallucinations or unreliable outputs
Considerations:
Manual checks required for safety
Additional Notes 
Developed with grants from Andreessen Horowitz (a16z)
Supported Languages 
en (general), zh (general)
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:
Identical structure to LLaMA2, using synthetic data
Model Architecture:
LLaMA2 architecture without scaling of RoPE
Safety Evaluation 
Risk Categories:
misinformation, bias, objectionable content, pornography, violence, offensive language
Ethical Considerations:
Model trained on unfiltered internet data
Responsible Ai Considerations 
Fairness:
Synthetic data utilized for some language variants
Accountability:
Developers have not vetted all content
Mitigation Strategies:
Users advised to filter certain keywords
Input Output 
Input Format:
ChatML prompt format
Accepted Modalities:
text
Output Format:
text
LLM NameCausalLM 7B GPTQ
Repository 🤗https://huggingface.co/TheBloke/CausalLM-7B-GPTQ 
Model NameCausalLM 7B
Model CreatorCausalLM
Base Model(s)  7B   CausalLM/7B
Model Size7b
Required VRAM5.9 GB
Updated2026-07-14
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  5.9 GB
Supported Languagesen zh
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensewtfpl
Context Length8192
Model Max Length8192
Transformers Version4.34.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size151936
Torch Data Typefloat16

Best Alternatives to CausalLM 7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB4927
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB60
...echless Tora Code 7B V1.0 GPTQ16K / 3.9 GB91
CodeLlama 7B Instruct GPTQ16K / 3.9 GB49946
Leo Hessianai 7B Chat GPTQ8K / 3.9 GB180
...ssianai 7B Chat Bilingual GPTQ8K / 3.9 GB60
Xgen 7B 8K Open Instruct Gptq8K / 4.2 GB54
Deepseek Math 7B Instruct GPTQ4K / 4.8 GB50
... Llama 2 7B Fast Instruct GPTQ4K / 4.1 GB953
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CausalLM-7B-GPTQ.