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

Llama Pile 350B by devingulliver

 »  All LLMs  »  devingulliver  »  Llama Pile 350B   URL Share it on

  66   
  Arxiv:1910.09700   Autotrain compatible   Endpoints compatible   Llama   Model-index   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/devingulliver/llama-pile-350b 

Llama Pile 350B Benchmarks

ARC: 33.19 vs 96.7 (so35)-65.7%
HellaSwag: 56.6 vs 95.3 (gpt4)-40.6%
MMLU: 24.66 vs 88.3 (so35)-72.1%
TruthfulQA: 36.28 vs 59 (gpt4)-38.5%
WinoGrande: 58.48 vs 87.5 (gpt4)-33.2%
GSM8K: 0.76 vs 96.4 (so35)-99.2%
LLME Score: 0.22095
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama Pile 350B (devingulliver/llama-pile-350b)

Llama Pile 350B Parameters and Internals

Model Type 
text-generation
Use Cases 
Considerations:
[More Information Needed]
Additional Notes 
Model card information is minimal with most sections labeled "More Information Needed."
Training Details 
Data Sources:
The Pile
Data Volume:
350B tokens
LLM NameLlama Pile 350B
Repository 🤗https://huggingface.co/devingulliver/llama-pile-350b 
Model Size350b
Required VRAM3.4 GB
Updated2025-03-22
Maintainerdevingulliver
Model Typellama
Model Files  3.4 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.37.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50272
Torch Data Typefloat16

Best Alternatives to Llama Pile 350B

Best Alternatives
Context / RAM
Downloads
Likes
Llama 350M16K / 0.7 GB00
...on Model On 350B FineWeb.seed18K / 27.4 GB3030
... Model On 350B GneissWeb.seed28K / 27.4 GB1300
... Model On 350B GneissWeb.seed38K / 27.4 GB1060
...on Model On 350B FineWeb.seed38K / 27.4 GB970
...odel On 350B FineWeb.Edu.seed18K / 27.4 GB1290
... Model On 350B GneissWeb.seed18K / 27.4 GB1170
...odel On 350B FineWeb.Edu.seed28K / 27.4 GB790
...odel On 350B FineWeb.Edu.seed38K / 27.4 GB700
...on Model On 350B FineWeb.seed28K / 27.4 GB640
Note: green Score (e.g. "73.2") means that the model is better than devingulliver/llama-pile-350b.

Rank the Llama Pile 350B 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? 45389 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 v20241227
  Support LLM Explorer