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

Prem 1B Chat 32K by ucalyptus

 »  All LLMs  »  ucalyptus  »  Prem 1B Chat 32K   URL Share it on

  4   
  Arxiv:2309.10400   Adapter Base model:adapter:premai-io/p... Base model:premai-io/prem-1b-c...   Finetuned   Generated from trainer   Llama   Lora   Peft   Region:us   Safetensors   Tensorboard
Model Card on HF 🤗: https://huggingface.co/ucalyptus/prem-1B-chat-32k 

Prem 1B Chat 32K Benchmarks

LLME Score: 0.15343
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Prem 1B Chat 32K (ucalyptus/prem-1B-chat-32k)
🌟 Advertise your project 🚀

Prem 1B Chat 32K Parameters and Internals

Model Type 
LlamaForCausalLM
Additional Notes 
The model was built using Axolotl, version 0.4.0, and employs strategies such as using a learning rate of 1e-05, Adam optimizer, and a cosine learning rate scheduler. Gradient checkpointing is used with multi-device setup.
Training Details 
Data Sources:
Argilla DPO dataset
Methodology:
The model is fine-tuned on the Argilla DPO dataset with 32K context extended using PoSE method.
Context Length:
8192
Hardware Used:
multi-GPU, num_devices: 8
LLM NamePrem 1B Chat 32K
Repository 🤗https://huggingface.co/ucalyptus/prem-1B-chat-32k 
Base Model(s)  Prem 1B Chat   premai-io/prem-1B-chat
Model Size1b
Required VRAM1.4 GB
Updated2025-10-10
Maintainerucalyptus
Model Files  1.4 GB
Model ArchitectureAdapter
Licenseapache-2.0
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|o_proj|v_proj|k_proj
LoRA Alpha1024
LoRA Dropout0.1
R Param1024

Best Alternatives to Prem 1B Chat 32K

Best Alternatives
Context / RAM
Downloads
Likes
...iabolic6045 ELN AOC CAIN QLoRA0K / 0 GB50
Llama 3.2 1B Airoboros Merged0K / 0.1 GB70
Openhermes 1B Olmo Sft Qlora0K / 0 GB50
Zephyr 1B Olmo Sft Qlora0K / 0 GB61
...la Alpaca Orca Instruct V0.0.10K / 1.1 GB140
Peft Starcoder Lora Python0K / 0 GB50
Prem 1B 32K0K / 1.4 GB41
...ama 3 1M Context Gradient Lora0K / 3.5 GB012
Falcon Arxiv Long Summary 1B0K / 0.2 GB71
...lcon 1B HomemadePromptImprover0K / 0 GB01
Note: green Score (e.g. "73.2") means that the model is better than ucalyptus/prem-1B-chat-32k.

Rank the Prem 1B Chat 32K 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? 51544 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 v20241124
  Support LLM Explorer