4-bit Autotrain compatible Base model:jeff31415/tinyllama... Base model:quantized:jeff31415... Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62... Dataset:open-orca/openorca En Gptq Llama Quantized Region:us Safetensors
TinyLlama 1.1B 1T OpenOrca GPTQ Parameters and Internals
| LLM Name | TinyLlama 1.1B 1T OpenOrca GPTQ |
| Repository | Open on 🤗 |
| Model Name | Tinyllama 1.1B 1T Openorca |
| Model Creator | jeff zhao |
| Base Model(s) | |
| Model Size | 627b |
| Required VRAM | 0.8 GB |
| Updated | 2024-07-26 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.34.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to TinyLlama 1.1B 1T OpenOrca GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| TinyLlama V1.1 | 0.3 | 2K / 4.4 GB | 82274 | 32 |
| CroissantLLMBase | 0.3 | 2K / 5.4 GB | 1802 | 29 |
| MicroLlama | 0.3 | 2K / 1.2 GB | 1026 | 36 |
| TinyLlama V1.1 Math Code | 0.3 | 2K / 4.4 GB | 4006 | 2 |
| TinyLlama V1.1 Chinese | 0.2 | 2K / 4.4 GB | 314 | 4 |
| ...Llama 1.1B 1.5T OpenOrca Alpha | 0.2 | 2K / 2.2 GB | 317 | 4 |
| TinyLlama 1.1B 1T OpenOrca | 0.2 | 2K / 2.2 GB | 350 | 7 |
| TinyLlama 1.1B 1T OpenOrca AWQ | 0.2 | 2K / 0.8 GB | 15 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/TinyLlama-1.1B-1T-OpenOrca-GPTQ .
Rank the TinyLlama 1.1B 1T OpenOrca 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501