Stablelm Base Alpha 7B Benchmarks
ARC: 32 vs 96.7 (so35)-66.9%
HellaSwag: 51.78 vs 95.3 (gpt4)-45.7%
MMLU: 26.21 vs 88.3 (so35)-70.3%
TruthfulQA: 40.19 vs 59 (gpt4)-31.9%
WinoGrande: 55.41 vs 87.5 (gpt4)-36.7%
GSM8K: 0.61 vs 96.4 (so35)-99.4%
LLME Score: 0.18492
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)
Stablelm Base Alpha 7B Parameters and Internals
| LLM Name | Stablelm Base Alpha 7B |
| Repository 🤗 | https://huggingface.co/stabilityai/stablelm-base-alpha-7b |
| Model Size | 7b |
| Required VRAM | 31.9 GB |
| Updated | 2024-10-18 |
| Maintainer | stabilityai |
| Model Type | gpt_neox |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPTNeoXForCausalLM |
| License | cc-by-sa-4.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.27.4 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float32 |
Best Alternatives to Stablelm Base Alpha 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Literature 7B 16384 | 16K / 36 GB | 33 | 14 |
| RedPajama 7B 16384 | 16K / 36 GB | 3 | 4 |
| Stablelm Tuned Alpha 7B | 4K / 31.9 GB | 2276 | 357 |
| Stablelm 7B Sft V7 Epoch 3 | 4K / 32.4 GB | 1248 | 67 |
| StableLManticore 7B | 4K / 16 GB | 4 | 1 |
| Pythia 6.9B Deduped 4K | 4K / 27.2 GB | 8 | 11 |
| Stablelm 7B | 4K / 31.9 GB | 0 | 2 |
| Sarashina1 7B | 2K / 13.9 GB | 779 | 0 |
| Dolly V2 7B | 2K / 13.8 GB | 13440 | 147 |
| Open Calm 7B | 2K / 13.9 GB | 2388 | 204 |
Note: green Score (e.g. "73.2") means that the model is better than stabilityai/stablelm-base-alpha-7b .
Rank the Stablelm Base Alpha 7B 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803