Autotrain compatible Codegen Endpoints compatible Fp8 Gpt bigcode Region:us Safetensors Sharded Tensorflow
Granite 20B Code Base FP8 Benchmarks
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 20B Code Base FP8 Parameters and Internals
| LLM Name | Granite 20B Code Base FP8 |
| Repository 🤗 | https://huggingface.co/nm-testing/granite-20b-code-base-FP8 |
| Model Size | 20b |
| Required VRAM | 20.4 GB |
| Updated | 2024-10-12 |
| Maintainer | nm-testing |
| Model Type | gpt_bigcode |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | GPTBigCodeForCausalLM |
| Model Max Length | 9223372036854775807 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu_pytorch_tanh |
Best Alternatives to Granite 20B Code Base FP8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Granite 20B Code Instruct | 0K / 40 GB | 10209 | 30 |
| Granite 20B Functioncalling | 0K / 40 GB | 543 | 26 |
| Granite 20B Code Base 8K | 0K / 40 GB | 7347 | 13 |
| Granite 20B Code Instruct 8K | 0K / 40 GB | 1177 | 37 |
| Granite 20B Code Base R1.1 | 0K / 40 GB | 261 | 2 |
| Granite 20B Code Base | 0K / 40 GB | 2250 | 12 |
| Granite 20B Code Instruct R1.1 | 0K / 40 GB | 44 | 1 |
| Granite 20B Code Base GGUF | 0K / 12.8 GB | 83 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than nm-testing/granite-20b-code-base-FP8 .
Rank the Granite 20B Code Base FP8 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? 36764 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803