SmolLM 135M Instruct Layer Pruned 90M Raw by Trelis

 ยป  All LLMs  ยป  Trelis  ยป  SmolLM 135M Instruct Layer Pruned 90M Raw   URL Share it on

  Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfacetb/smoll...   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors

SmolLM 135M Instruct Layer Pruned 90M Raw Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SmolLM 135M Instruct Layer Pruned 90M Raw (Trelis/SmolLM-135M-Instruct-layer-pruned-90M-raw)

SmolLM 135M Instruct Layer Pruned 90M Raw Parameters and Internals

Additional Notes 
Layers are removed from the top of the model (except for the last layer) in order to reduce the parameter count to approximately 99M.
LLM NameSmolLM 135M Instruct Layer Pruned 90M Raw
Repository ๐Ÿค—https://huggingface.co/Trelis/SmolLM-135M-Instruct-layer-pruned-90M-raw 
Base Model(s)  SmolLM 135M Instruct   HuggingFaceTB/SmolLM-135M-Instruct
Model Size135m
Required VRAM0.2 GB
Updated2025-02-14
MaintainerTrelis
Model Typellama
Instruction-BasedYes
Model Files  0.2 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.44.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolLM 135M Instruct Layer Pruned 90M Raw

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 135M Instruct8K / 0.3 GB141697127
Reasoning SmolLM2 135M8K / 0.5 GB28211
Jaja Small V48K / 0.5 GB560
...wre324 R1 SmolLM2 135M Distill8K / 0.5 GB230
...molLM2 135M Instruct Reasoning8K / 0.3 GB70
SmolLM2 135M Instruct8K / 0.3 GB8632
Autotrain 0tmgq 5tpbg8K / 0.3 GB1580
Smollm 135M Full Fineweb Is8K / 0.5 GB180
...molLM2 135M Instruct Reasoning8K / 0.3 GB280
SmolLM2 Prompt Enhance8K / 0.5 GB2057
Note: green Score (e.g. "73.2") means that the model is better than Trelis/SmolLM-135M-Instruct-layer-pruned-90M-raw.

Rank the SmolLM 135M Instruct Layer Pruned 90M Raw Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43106 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227