Merged Model Autotrain compatible Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow
Pruned Yi 3B Prerelease Ckpt01 Benchmarks
ARC: 24.4 vs 96.7 (so35)-74.8%
HellaSwag: 31.6 vs 95.3 (gpt4)-66.8%
MMLU: 25.18 vs 88.3 (so35)-71.5%
TruthfulQA: 46.05 vs 59 (gpt4)-21.9%
WinoGrande: 51.14 vs 87.5 (gpt4)-41.6%
GSM8K: 0.08 vs 96.4 (so35)-99.9%
LLME Score: 0.27544
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)
Pruned Yi 3B Prerelease Ckpt01 Parameters and Internals
| LLM Name | Pruned Yi 3B Prerelease Ckpt01 |
| Repository 🤗 | https://huggingface.co/pruned-yi/pruned-yi-3b-prerelease-ckpt01 |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2024-08-13 |
| Maintainer | pruned-yi |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Pruned Yi 3B Prerelease Ckpt01
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.1 Mini Instruct | 128K / 6.1 GB | 60 | 0 |
| Granite 3B Code Instruct 128K | 125K / 7 GB | 282 | 2 |
| Granite 3B Code Base 128K | 125K / 7 GB | 340 | 1 |
| Openbuddy Zero 3B V21.2 32K | 32K / 9.5 GB | 44 | 2 |
| Openbuddy Zen 3B V21.1 32K | 32K / 9.5 GB | 11 | 2 |
| Mm4.more.star | 32K / 6 GB | 4 | 1 |
| Mm4.ascii.star | 32K / 6 GB | 5 | 0 |
| KoreanLM 3B | 20K / 11.4 GB | 2061 | 0 |
| Buzz 3B Small V0.6.3 | 8K / 8.7 GB | 6 | 1 |
| Deacon 3B | 8K / 13.7 GB | 1359 | 2 |
Rank the Pruned Yi 3B Prerelease Ckpt01 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803