LLM Name | Prem 1B Chat Onnx Q4 |
Repository | Open on ๐ค |
Base Model(s) | |
Model Size | 1b |
Updated | 2024-07-27 |
Maintainer | ucalyptus |
Model Type | llama |
Quantization Type | q4 |
Model Architecture | LlamaForCausalLM |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.38.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | [PAD] |
Vocabulary Size | 32004 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...les 32K Bf16 V1.4.0bpw H6 EXL2 | 0.2 | 32K / 18.1 GB | 13 | 2 |
...les 32K Bf16 V1.5.0bpw H6 EXL2 | 0.2 | 32K / 22.2 GB | 12 | 2 |
...les 32K Bf16 V1.6.0bpw H6 EXL2 | 0.2 | 32K / 26.5 GB | 6 | 1 |
...lama 3 1B Awarri Instruct 4bit | 0.2 | 8K / 5.8 GB | 27 | 0 |
Rho Math 1B V0.1 4bit | 0.3 | 2K / 0.7 GB | 10 | 1 |
... Math 1B Interpreter V0.1 4bit | 0.2 | 2K / 0.7 GB | 9 | 1 |
...1B Chat V1.0 AQLM 2Bit 1x16 Hf | 0.2 | 2K / 0.7 GB | 167 | 0 |
LWM Text Chat 1M | 0.3 | 1024K / 13.5 GB | 1222 | 172 |
LWM Text 1M | 0.2 | 1024K / 13.5 GB | 21 | 27 |
JOSIE 1M Base | 0.2 | 1024K / 13.5 GB | 5 | 1 |
๐ 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! ๐