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

AMD Llama 135M by amd

 »  All LLMs  »  amd  »  AMD Llama 135M   URL Share it on

  17707   
  Arxiv:2204.06745   Autotrain compatible Dataset:cerebras/slimpajama-62...   Dataset:manu/project gutenberg   Endpoints compatible   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/amd/AMD-Llama-135m 

AMD Llama 135M Benchmarks

MMLU Pro: 1.87
GPQA: 1.12
MUSR: 5.9
BBH: 2.54
IFEval: 19.18 vs 88 (so35)-78.2%
MATH Lvl 5: 0.76
LLME Score: 0.29051
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
AMD Llama 135M (amd/AMD-Llama-135m)

AMD Llama 135M Parameters and Internals

Model Type 
language model
Training Details 
Data Sources:
cerebras/SlimPajama-627B, manu/project_gutenberg
Data Volume:
670B training tokens
Context Length:
2048
Training Time:
6 days for pretraining, 4 days for finetuning
Hardware Used:
4 MI250 nodes, each with 4 MI250 GPUs
Model Architecture:
Based on LLaMA2 model architecture
LLM NameAMD Llama 135M
Repository 🤗https://huggingface.co/amd/AMD-Llama-135m 
Model Size135m
Required VRAM0.5 GB
Updated2025-02-22
Maintaineramd
Model Typellama
Model Files  0.5 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to AMD Llama 135M

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 135M Instruct8K / 0.3 GB163667139
SmolLM2 135M8K / 0.3 GB23397962
SmolLM2 135M Grpo Gsm8k8K / 0.5 GB19511
SmolLM2 135M8K / 0.3 GB68701
Jaja Small V48K / 0.5 GB1420
Reasoning SmolLM2 135M8K / 0.5 GB24311
... Fineweb Uncovai Human Removed8K / 0.5 GB210
...wre324 R1 SmolLM2 135M Distill8K / 0.5 GB250
SmolLM2 FT MyDataset8K / 0.5 GB280
Jaja Small8K / 0.5 GB1220
Note: green Score (e.g. "73.2") means that the model is better than amd/AMD-Llama-135m.

Rank the AMD Llama 135M 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? 43470 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