Pythia 1.4B Sft Full by nnheui

 »  All LLMs  »  nnheui  »  Pythia 1.4B Sft Full   URL Share it on

Pythia 1.4B Sft Full is an open-source language model by nnheui. Features: 1.4b LLM, VRAM: 2.8GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.16, Arc: 32.7, HellaSwag: 52.1, MMLU: 25.4, GSM8K: 2.

  Alignment-handbook Base model:eleutherai/pythia-1... Base model:finetune:eleutherai...   Conversational Dataset:huggingfaceh4/ultracha...   Endpoints compatible   Generated from trainer   Gpt neox   Region:us   Safetensors

Pythia 1.4B Sft Full Benchmarks

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

Pythia 1.4B Sft Full Parameters and Internals

Training Details 
Data Sources:
HuggingFaceH4/ultrachat_200k
Hardware Used:
multi-GPU, 4 devices
LLM NamePythia 1.4B Sft Full
Repository 🤗https://huggingface.co/nnheui/pythia-1.4b-sft-full 
Base Model(s)  EleutherAI/pythia-1.4b   EleutherAI/pythia-1.4b
Model Size1.4b
Required VRAM2.8 GB
Updated2026-05-09
Maintainernnheui
Model Typegpt_neox
Model Files  2.8 GB
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.36.2
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|endoftext|>
Vocabulary Size50304
Torch Data Typebfloat16

Best Alternatives to Pythia 1.4B Sft Full

Best Alternatives
Context / RAM
Downloads
Likes
Pythia 1.4B Deduped 8K Base8K / 7.3 GB41
Violet 1b4 Chat4K / 2.8 GB127
Pythia 1.4B Deduped 4K Base4K / 6.1 GB52
Statichh Pythia 1.4B Sft Bf162K / 5.7 GB50
Pythia 1.4B2K / 2.9 GB7001326
Pythia 1.4B Deduped2K / 5.7 GB1877421
Pythia 1.4B Deduped Sharegpt2K / 2.8 GB9942
Pythia Delphi Suboptimal2K / 5.7 GB60
Pythia 1.4B Deduped Sharegpt2K / 2.8 GB10180
RCC Ins Reconstruction2K / 6.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than nnheui/pythia-1.4b-sft-full.

Rank the Pythia 1.4B Sft Full 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? 54415 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a