4-bit 4bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Mistral Quantized Region:us Safetensors
Mcqa 4bit 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)
Mcqa 4bit Parameters and Internals
| LLM Name | Mcqa 4bit |
| Repository 🤗 | https://huggingface.co/yfdeng/mcqa-4bit |
| Model Size | 3.9b |
| Required VRAM | 4.1 GB |
| Updated | 2024-09-07 |
| Maintainer | yfdeng |
| Model Type | mistral |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32002 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mcqa 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Spydaz Web AI 026 4bit | 32K / 4.2 GB | 23 | 0 |
| ...cr To Json V1 Bnb 4bit Smashed | 32K / 4.5 GB | 16 | 0 |
| Mixtral AI SwahiliTron 4BIT | 32K / 4.1 GB | 5 | 0 |
| Mistral 4bit Bnb | 32K / 4.1 GB | 5 | 0 |
| Yugo55 GPT V4 4bit | 32K / 4.1 GB | 504 | 1 |
| Rezephyr Merged 4bit | 32K / 4.1 GB | 60 | 0 |
| Zephyr DPO 4bit | 32K / 4.1 GB | 62 | 0 |
| ...Spydaz Web AI ChatQA 003 4 BIT | 512K / 4.1 GB | 54 | 0 |
| ...Spydaz Web AI ChatQA 002 4 BIT | 512K / 4.1 GB | 51 | 0 |
| ...ydaz Web AI ChatQA 002r1 4 BIT | 512K / 4.1 GB | 46 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than yfdeng/mcqa-4bit .
Rank the Mcqa 4bit 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