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

7B by CausalLM

 »  All LLMs  »  CausalLM  »  7B   URL Share it on

  3   
  Autotrain compatible   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   Endpoints compatible   Instruct   Llama   Llama2   Pytorch   Qwen   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/CausalLM/7B 

7B Benchmarks

ARC: 50 vs 96.7 (so35)-48.3%
HellaSwag: 74.58 vs 95.3 (gpt4)-21.7%
MMLU: 61.79 vs 88.3 (so35)-30%
TruthfulQA: 50.13 vs 59 (gpt4)-15%
WinoGrande: 69.69 vs 87.5 (gpt4)-20.4%
GSM8K: 22.97 vs 96.4 (so35)-76.2%
LLME Score: 0.18719
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
7B (CausalLM/7B)

7B Parameters and Internals

Model Type 
text generation, causallm
Use Cases 
Areas:
research, commercial applications
Limitations:
May produce hallucinations or unreliable outputs., Trained on unfiltered internet data, potentially contains objectionable content.
Considerations:
Users should implement safety checks and filter keywords in outputs.
Additional Notes 
The 7B version is a distilled version of the 14B model.
Supported Languages 
en (English: high proficiency), zh (Chinese: high 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:
Manually curated SFT dataset, synthetic data generation using larger language models.
Model Architecture:
Same as LLaMA2 with original MHA LLaMA2 models; no additional scaling for RoPE.
Input Output 
Input Format:
chatml
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Avoid unofficial GPTQ and AWQ models; prefer GGUF for quantization.
LLM Name7B
Repository 🤗https://huggingface.co/CausalLM/7B 
Model Size7b
Required VRAM15.5 GB
Updated2024-12-22
MaintainerCausalLM
Model Typellama
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   5.5 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureLlamaForCausalLM
Licensewtfpl
Context Length8192
Model Max Length8192
Transformers Version4.35.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size151936
Torch Data Typebfloat16

Quantized Models of the 7B

Model
Likes
Downloads
VRAM
CausalLM 7B GGUF5632103 GB
CausalLM 7B GPTQ5595 GB
CausalLM 7B AWQ3315 GB

Best Alternatives to 7B

Best Alternatives
Context / RAM
Downloads
Likes
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB29350
SuperNeuralDreadDevil 8B128K / 16.1 GB1551
Falcon3 7B Instruct32K / 14.8 GB411428
Falcon3 7B Instruct 1.58bit32K / 3.3 GB44113
FalconSlerp2 7B32K / 14.9 GB60
Llama 2 7B 32K Instruct32K / 13.5 GB6101159
Qwen2 7B Instruct Llama32K / 15.2 GB113
Qwen2 7B Instruct Mistral32K / 15.2 GB141
AIRIC The Mistral32K / 14.4 GB7507
...ls Vikhr 7B Instruct 0.4 4bits32K / 5.2 GB100
Note: green Score (e.g. "73.2") means that the model is better than CausalLM/7B.

Rank the 7B 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