Palmyra Large is an open-source language model by Writer. Features: LLM, VRAM: 41.6GB, License: apache-2.0, HF Score: 42.1, Arc: 45, HellaSwag: 71.9, MMLU: 28.5, TruthfulQA: 35.9, WinoGrande: 67.9, GSM8K: 3.4.
Dataset:english Dataset:writer/palmyra-data-in... En Endpoints compatible Gpt Gpt2 Palmyra Pytorch Region:us Safetensors Sharded Tensorflow Writer-data
Model Card on HF 🤗: https://huggingface.co/Writer/palmyra-large
Palmyra Large Benchmarks
ARC: 44.97 vs 96.7 (so35)-53.5%
HellaSwag: 71.85 vs 95.3 (gpt4)-24.6%
MMLU: 28.54 vs 88.3 (so35)-67.7%
TruthfulQA: 35.93 vs 59 (gpt4)-39.1%
WinoGrande: 67.88 vs 87.5 (gpt4)-22.4%
GSM8K: 3.41 vs 96.4 (so35)-96.5%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Palmyra Large Parameters and Internals
| LLM Name | Palmyra Large |
| Repository 🤗 | https://huggingface.co/Writer/palmyra-large |
| Required VRAM | 41.6 GB |
| Updated | 2026-03-27 |
| Maintainer | Writer |
| Model Type | gpt2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPT2LMHeadModel |
| License | apache-2.0 |
| Model Max Length | 1024 |
| Transformers Version | 4.21.2 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 50257 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu |
Best Alternatives to Palmyra Large
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gpt2 Base Bne | 0K / 0.5 GB | 1736 | 0 |
| Chatbench Distilgpt2 | 0K / 0.3 GB | 92 | 3 |
| Hanuman | 0K / 0.5 GB | 63 | 0 |
| BrtGPT 1 Pre | 0K / 0.4 GB | 132 | 0 |
| GPT 2 Large 115K Steps | 0K / 0 GB | 8 | 0 |
| GPT 2 Large 51K Steps | 0K / 0 GB | 6 | 0 |
| GPT 2 Large 40K Steps | 0K / 0 GB | 6 | 0 |
| GPT 2 Large 20K Steps | 0K / 0 GB | 8 | 0 |
| GPT 2 Large 32K Steps | 0K / 0 GB | 5 | 0 |
| GPT 2 Large 43K Steps | 0K / 0 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Writer/palmyra-large .
Rank the Palmyra Large 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! 🌟
What open-source LLMs or SLMs are you in search of? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b