Arxiv:2307.09288 4-bit Autotrain compatible Base model:cognitivecomputatio... Base model:quantized:cognitive... En Gptq Llama Quantized Region:us Safetensors Zh
Model Card on HF 🤗: https://huggingface.co/TheBloke/yayi2-30B-llama-GPTQ
Yayi2 30B Llama GPTQ 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)
Yayi2 30B Llama GPTQ Parameters and Internals
| LLM Name | Yayi2 30B Llama GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/yayi2-30B-llama-GPTQ |
| Model Name | Yayi2 30B Llama |
| Model Creator | Cognitive Computations |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 17 GB |
| Updated | 2025-02-22 |
| Maintainer | TheBloke |
| Model Type | yayi2 |
| Model Files | |
| Supported Languages | zh en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 81920 |
| Torch Data Type | float16 |
Best Alternatives to Yayi2 30B Llama GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GPlatty 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 18 | 7 |
| ... 30B Supercot SuperHOT 8K GPTQ | 8K / 16.9 GB | 21 | 5 |
| Platypus 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 18 | 4 |
| Tulu 30B SuperHOT 8K GPTQ | 8K / 16.9 GB | 15 | 5 |
| WizardLM 30B GPTQ | 2K / 16.9 GB | 2009 | 19 |
| Llama 30B FINAL MODEL MINI | 2K / 19.4 GB | 5 | 1 |
| ...2 Llama 30B 7K Steps Gptq 2bit | 2K / 9.5 GB | 9 | 2 |
| ...Assistant SFT 7 Llama 30B GPTQ | 2K / 16.9 GB | 2042 | 35 |
| WizardLM 30B V1.0 GPTQ | 2K / 16.9 GB | 3 | 1 |
| ...2 Llama 30B 7K Steps Gptq 4bit | 2K / 17.5 GB | 7 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/yayi2-30B-llama-GPTQ .
Rank the Yayi2 30B Llama GPTQ 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227