Model Card on HF 🤗: https://huggingface.co/jackboot/quill-57b-tokenizer
Quill 57B Tokenizer 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)
Quill 57B Tokenizer Parameters and Internals
| Additional Notes |
|
| LLM Name | Quill 57B Tokenizer |
| Repository 🤗 | https://huggingface.co/jackboot/quill-57b-tokenizer |
| Model Size | 57b |
| Updated | 2025-09-23 |
| Maintainer | jackboot |
| Model Type | qwen2_moe |
| Model Architecture | Qwen2MoeForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Quill 57B Tokenizer
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 57B A14B | 128K / 115.2 GB | 11692 | 52 |
| Qwen2 57B A14B Instruct | 32K / 115.2 GB | 10108 | 81 |
| Qwen2 57B A14B Instruct 4bit | 32K / 32.3 GB | 14 | 2 |
| Qwen2 57B A14B Instruct 8bit | 32K / 61.1 GB | 4 | 1 |
| ...n2 57B A14B Instruct GPTQ Int4 | 32K / 31.6 GB | 84 | 23 |
| ...7B A14B Instruct GPTQ Int4 MLX | 32K / 32.3 GB | 47 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than jackboot/quill-57b-tokenizer .
Rank the Quill 57B Tokenizer 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? 51611 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124