Granite 7B Base Benchmarks
MMLU Pro: 9.27
MUSR: 3.4
BBH: 9.05
IFEval: 24.14 vs 88 (so35)-72.6%
MATH Lvl 5: 0.6
LLME Score: 0.30001
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)
Granite 7B Base Parameters and Internals
| LLM Name | Granite 7B Base |
| Repository 🤗 | https://huggingface.co/ibm-granite/granite-7b-base |
| Model Size | 7b |
| Required VRAM | 27.1 GB |
| Updated | 2024-09-08 |
| Maintainer | ibm-granite |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Granite 7B Base
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...1M 1000000ctx AEZAKMI 3 1 1702 | 1024K / 13.5 GB | 62 | 1 |
| Yarn Llama 2 7B 128K | 128K / 13.5 GB | 497 | 38 |
| LLaMA 7B PoSE YaRN 128K | 128K / 13.5 GB | 17 | 3 |
| LLaMA 7B PoSE Linear 96K | 96K / 27 GB | 6 | 2 |
| LLaMA 7B PoSE YaRN 96K | 96K / 13.5 GB | 7 | 1 |
| Chat Llama2 7B 80K | 80K / 13.8 GB | 6 | 0 |
| Llama2 7B 80K | 80K / 13.8 GB | 7 | 0 |
| Lloma Step400 | 64K / 13.5 GB | 57 | 0 |
| Lloma Step200 | 64K / 13.5 GB | 62 | 0 |
| Lloma Step50 | 64K / 13.5 GB | 57 | 0 |
Rank the Granite 7B Base 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