Autotrain compatible Base model:amazingvince/zephyr... Base model:finetune:amazingvin... Conversational Endpoints compatible Generated from trainer Llama Region:us Safetensors Tensorboard
Model Card on HF 🤗: https://huggingface.co/amazingvince/zephyr-smol_llama-100m-dpo-full
Zephyr Smol Llama 100M DPO Full Benchmarks
ARC: 25 vs 96.7 (so35)-74.1%
HellaSwag: 28.54 vs 95.3 (gpt4)-70.1%
MMLU: 25.18 vs 88.3 (so35)-71.5%
TruthfulQA: 45.75 vs 59 (gpt4)-22.5%
WinoGrande: 51.07 vs 87.5 (gpt4)-41.6%
GSM8K: 0.68 vs 96.4 (so35)-99.3%
LLME Score: 0.19555
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)
Zephyr Smol Llama 100M DPO Full Parameters and Internals
| Additional Notes |
|
| LLM Name | Zephyr Smol Llama 100M DPO Full |
| Repository 🤗 | https://huggingface.co/amazingvince/zephyr-smol_llama-100m-dpo-full |
| Base Model(s) | |
| Model Size | 100m |
| Required VRAM | 0.2 GB |
| Updated | 2025-02-05 |
| Maintainer | amazingvince |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 1024 |
| Model Max Length | 1024 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32128 |
| Torch Data Type | bfloat16 |
Best Alternatives to Zephyr Smol Llama 100M DPO Full
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmollerLM2 100M Instruct Sft | 8K / 0.3 GB | 52 | 0 |
| SmollerLM2 100M | 8K / 0.2 GB | 41 | 0 |
| Stockmark 100B | 4K / 191.9 GB | 160 | 33 |
| Saily 100b | 4K / 235.5 GB | 1352 | 7 |
| Plankton 100M | 4K / 0.4 GB | 158 | 0 |
| ...lisLM 100M Layer Hidden Pruned | 2K / 0.2 GB | 820 | 0 |
| Reglu 100B | 2K / 2.6 GB | 7 | 1 |
| Llama 161M 100B | 1K / 0.3 GB | 48 | 23 |
| ...ephyr Smol Llama 100M DPO Full | 1K / GB | 15 | 1 |
| ...yr Smol Llama 100M DPO 1 Epoch | 1K / 0.2 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than amazingvince/zephyr-smol_llama-100m-dpo-full .
Rank the Zephyr Smol Llama 100M DPO Full 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227