Prem 1B Chat Onnx Q4 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)
Prem 1B Chat Onnx Q4 Parameters and Internals
| LLM Name | Prem 1B Chat Onnx Q4 |
| Repository 🤗 | https://huggingface.co/ucalyptus/prem-1B-chat-onnx-q4 |
| Base Model(s) | |
| Model Size | 1b |
| Updated | 2024-09-07 |
| 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 to Prem 1B Chat Onnx Q4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...les 32K Bf16 V1.4.0bpw H6 EXL2 | 32K / 18.1 GB | 18 | 2 |
| ...les 32K Bf16 V1.5.0bpw H6 EXL2 | 32K / 22.2 GB | 18 | 2 |
| ...les 32K Bf16 V1.6.0bpw H6 EXL2 | 32K / 26.5 GB | 20 | 1 |
| ...lama 3 1B Awarri Instruct 4bit | 8K / 5.8 GB | 11 | 0 |
| Rho Math 1B V0.1 4bit | 2K / 0.7 GB | 5 | 1 |
| ... Math 1B Interpreter V0.1 4bit | 2K / 0.7 GB | 6 | 1 |
| ...1B Chat V1.0 AQLM 2Bit 1x16 Hf | 2K / 0.7 GB | 159 | 0 |
| LWM Text Chat 1M | 1024K / 13.5 GB | 528 | 174 |
| JOSIE 1M Base | 1024K / 13.5 GB | 10 | 1 |
| LWM Text 1M | 1024K / 13.5 GB | 22 | 27 |
Note: green Score (e.g. "73.2") means that the model is better than ucalyptus/prem-1B-chat-onnx-q4 .
Rank the Prem 1B Chat Onnx Q4 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803