Base model:ewre324/ewre324-thi... Base model:finetune:ewre324/ew... Dataset:huggingfaceh4/bespoke-... Instruct Llama Region:us Safetensors Tensorboard
Model Card on HF 🤗: https://huggingface.co/ewre324/ewre324-R1-SmolLM2-135M-Distill
Ewre324 R1 SmolLM2 135M Distill Benchmarks
MMLU Pro: 1.48
GPQA: 1.57
MUSR: 0.78
BBH: 3.38
IFEval: 16.49 vs 88 (so35)-81.3%
MATH Lvl 5: 1.28
LLME Score: 0.25642
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)
Ewre324 R1 SmolLM2 135M Distill Parameters and Internals
| LLM Name | Ewre324 R1 SmolLM2 135M Distill |
| Repository 🤗 | https://huggingface.co/ewre324/ewre324-R1-SmolLM2-135M-Distill |
| Base Model(s) | |
| Model Size | 135m |
| Required VRAM | 0.5 GB |
| Updated | 2025-03-12 |
| Maintainer | ewre324 |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.49.0.dev0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49152 |
| Torch Data Type | float32 |
Best Alternatives to Ewre324 R1 SmolLM2 135M Distill
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 135M Instruct | 8K / 0.3 GB | 195185 | 151 |
| SmolLM2 135M Grpo Gsm8k | 8K / 0.5 GB | 378 | 13 |
| ...rtis SmolLM2 135M Instruct DPO | 8K / 0.5 GB | 229 | 0 |
| Reasoning SmolLM2 135M | 8K / 0.5 GB | 712 | 13 |
| Kurtis SmolLM2 135M Instruct | 8K / 0.5 GB | 50 | 0 |
| Jaja Small V4 | 8K / 0.5 GB | 156 | 0 |
| ...molLM2 135M Instruct Reasoning | 8K / 0.3 GB | 7 | 0 |
| Smollm 135M Full Fineweb Is | 8K / 0.5 GB | 16 | 0 |
| Autotrain 0tmgq 5tpbg | 8K / 0.3 GB | 41 | 0 |
| SmolLM2 135M Instruct | 8K / 0.3 GB | 429 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than ewre324/ewre324-R1-SmolLM2-135M-Distill .
Rank the Ewre324 R1 SmolLM2 135M Distill 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? 44887 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227