Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Conversational En Endpoints compatible Instruct Llama Onnx Region:us Safetensors Transformers.js
Model Card on HF 🤗: https://huggingface.co/ewre324/Thinker-SmolLM2-135M-Instruct-Reasoning
Thinker SmolLM2 135M Instruct Reasoning Benchmarks
MMLU Pro: 1.04
GPQA: 0.34
MUSR: 2.97
BBH: 3.97
IFEval: 25.84 vs 88 (so35)-70.6%
MATH Lvl 5: 0.15
LLME Score: 0.26724
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)
Thinker SmolLM2 135M Instruct Reasoning Parameters and Internals
| LLM Name | Thinker SmolLM2 135M Instruct Reasoning |
| Repository 🤗 | https://huggingface.co/ewre324/Thinker-SmolLM2-135M-Instruct-Reasoning |
| Base Model(s) | |
| Model Size | 135m |
| Required VRAM | 0.3 GB |
| Updated | 2025-01-11 |
| Maintainer | ewre324 |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to Thinker SmolLM2 135M Instruct Reasoning
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 135M Instruct | 8K / 0.3 GB | 40400 | 89 |
| Reasoning SmolLM2 135M | 8K / 0.5 GB | 380 | 9 |
| SmolLM2 135M Instruct | 8K / 0.3 GB | 903 | 0 |
| Autotrain 0tmgq 5tpbg | 8K / 0.3 GB | 112 | 0 |
| ...molLM2 135M Instruct Reasoning | 8K / 0.3 GB | 14 | 0 |
| SmolLM2 Prompt Enhance | 8K / 0.5 GB | 137 | 6 |
| SmolLM2 135M Instruct | 8K / 0.3 GB | 44 | 0 |
| SmolLM 135M Instruct | 2K / 0.3 GB | 17660 | 103 |
| SmolLM 135M Instruct | 2K / 0.3 GB | 2968 | 0 |
| SmolLM 135M | 2K / 0.3 GB | 2925 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ewre324/Thinker-SmolLM2-135M-Instruct-Reasoning .
Rank the Thinker SmolLM2 135M Instruct Reasoning 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? 41680 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227