4-bit 4bit Autotrain compatible Base model:mediatek-research/b... Base model:quantized:mediatek-... Bitsandbytes Conversational Endpoints compatible Instruct Mistral Pruna-ai Quantized Region:us Safetensors
MediaTek Research Breeze 7B Instruct V1.0 Bnb 4bit Smashed 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)
MediaTek Research Breeze 7B Instruct V1.0 Bnb 4bit Smashed Parameters and Internals
| LLM Name | MediaTek Research Breeze 7B Instruct V1.0 Bnb 4bit Smashed |
| Repository 🤗 | https://huggingface.co/PrunaAI/MediaTek-Research-Breeze-7B-Instruct-v1_0-bnb-4bit-smashed |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.9 GB |
| Updated | 2024-10-17 |
| Maintainer | PrunaAI |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 61952 |
| Torch Data Type | float16 |
Best Alternatives to MediaTek Research Breeze 7B Instruct V1.0 Bnb 4bit Smashed
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...al Nemo Instruct 2407 Bnb 4bit | 1000K / 8.3 GB | 21809 | 22 |
| ...tral 7B Instruct V0.3 Bnb 4bit | 32K / 4.1 GB | 75229 | 14 |
| Mistral 7B Instruct V0.2 Fp16 | 32K / 14.4 GB | 5 | 0 |
| Mistral 7B Instruct V0.2 4bit | 32K / 4.3 GB | 355 | 1 |
| Mistral 7B V0.3 Bnb 4bit | 32K / 4.1 GB | 13516 | 11 |
| ...tral 7B Instruct V0.2 Bnb 4bit | 32K / 4.1 GB | 10045 | 31 |
| Mistral 7B Instruct V0.2 8bit | 32K / 7.6 GB | 6 | 1 |
| Mistral Turkish V2 | 32K / 14.4 GB | 3215 | 6 |
| Minirewrite | 32K / 15.8 GB | 5 | 0 |
| Mistral7B MatheoAI8 Lora | 32K / 14.4 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/MediaTek-Research-Breeze-7B-Instruct-v1_0-bnb-4bit-smashed .
Rank the MediaTek Research Breeze 7B Instruct V1.0 Bnb 4bit Smashed 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803