Arxiv:2104.09864 Arxiv:2305.13711 4-bit Autotrain compatible Dataset:yentinglin/traditional... Dataset:yentinglin/zh tw c4 Endpoints compatible Gptq Instruct Llama Pytorch Quantized Region:us Zh
Taiwan LLaMa V1.0 4bits 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)
Taiwan LLaMa V1.0 4bits GPTQ Parameters and Internals
| LLM Name | Taiwan LLaMa V1.0 4bits GPTQ |
| Repository 🤗 | https://huggingface.co/q-allen/Taiwan-LLaMa-v1.0-4bits-GPTQ |
| Model Name | Language Models for Taiwanese Culture 1.0 |
| Required VRAM | 7.3 GB |
| Updated | 2024-09-18 |
| Maintainer | q-allen |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Taiwan LLaMa V1.0 4bits GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Taiwan LLaMa V1.0 4bits GPTQ | 4K / 7.3 GB | 25 | 9 |
| Phi 3.5 Instruct Vul | 128K / 7.6 GB | 40 | 0 |
| ...ene Phi 3.5 Mini Instruct Orpo | 128K / 7.6 GB | 31 | 1 |
| ...Instruct DPO V2.8.0bpw H8 EXL2 | 4K / 10.9 GB | 8 | 2 |
| Reverse Instruct | 32K / 27 GB | 7 | 3 |
| Codellama Cairo Instruct GGUF | 16K / 4.1 GB | 23 | 0 |
| Etri Ones Solar | 4K / 42.9 GB | 91 | 0 |
| Law Chat | 4K / 27 GB | 909 | 33 |
| Phi 3 Orpo V8.16 | 4K / 7.6 GB | 15 | 0 |
| Small Instruct | 4K / 2.9 GB | 4232 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than q-allen/Taiwan-LLaMa-v1.0-4bits-GPTQ .
Rank the Taiwan LLaMa V1.0 4bits 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803