Autotrain compatible Codegen Custom code Endpoints compatible Exl2 Fp16 Llama Pytorch Quantized Region:us
Trinity 13B 3.0bpw H6 EXL2 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)
Trinity 13B 3.0bpw H6 EXL2 Parameters and Internals
| LLM Name | Trinity 13B 3.0bpw H6 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/Trinity-13B-3.0bpw-h6-exl2 |
| Model Size | 13b |
| Required VRAM | 5.2 GB |
| Updated | 2024-09-16 |
| Maintainer | LoneStriker |
| Model Type | llama |
| Model Files | |
| Quantization Type | fp16|exl2 |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | CodeLlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32016 |
| Torch Data Type | bfloat16 |
Best Alternatives to Trinity 13B 3.0bpw H6 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| WhiteRabbitNeo 13B V1 | 16K / 26 GB | 1441 | 380 |
| CodeLlama 13B Python Fp16 | 16K / 26 GB | 1437 | 25 |
| CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 1441 | 29 |
| Codellama 13B Bnb 4bit | 16K / 7.2 GB | 72 | 1 |
| ...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 8 | 2 |
| CodeLlama 13B Fp16 | 16K / 26 GB | 14 | 66 |
| Trinity 13B | 16K / 26 GB | 6 | 15 |
| ...13B Instruct Nf4 Fp16 Upscaled | 16K / 26 GB | 322 | 0 |
| Trinity 13B 6.0bpw H6 EXL2 | 16K / 10 GB | 4 | 2 |
| Trinity 13B 4.0bpw H6 EXL2 | 16K / 6.8 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Trinity-13B-3.0bpw-h6-exl2 .
Rank the Trinity 13B 3.0bpw H6 EXL2 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? 35926 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803