Autotrain compatible B1ade Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol... En Endpoints compatible Gpt neox Instruct Pytorch Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/w601sxs/b1ade-1b
B1ade 1B Benchmarks
ARC: 28.58 vs 96.7 (so35)-70.4%
HellaSwag: 46.08 vs 95.3 (gpt4)-51.6%
MMLU: 25.11 vs 88.3 (so35)-71.6%
TruthfulQA: 41.34 vs 59 (gpt4)-29.9%
WinoGrande: 53.83 vs 87.5 (gpt4)-38.5%
GSM8K: 0.61 vs 96.4 (so35)-99.4%
LLME Score: 0.18075
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)
B1ade 1B Parameters and Internals
| Supported Languages |
|
| LLM Name | B1ade 1B |
| Repository 🤗 | https://huggingface.co/w601sxs/b1ade-1b |
| Model Size | 1b |
| Required VRAM | 2 GB |
| Updated | 2025-02-22 |
| Maintainer | w601sxs |
| Model Type | gpt_neox |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPTNeoXForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50304 |
| Torch Data Type | float32 |
Best Alternatives to B1ade 1B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...hia 1B Deduped Instruct Ckpt 1 | 2K / 2.1 GB | 60 | 0 |
| ...hia 1B Deduped Instruct Ckpt 2 | 2K / 2.1 GB | 59 | 0 |
| Expert Min Pile Instruct | 2K / 2.1 GB | 5 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than w601sxs/b1ade-1b .
Rank the B1ade 1B 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227