4-bit 4bit Autotrain compatible Bitsandbytes Bnb En Endpoints compatible Mistral Mistral-7b Quantized Region:us Safetensors Unsloth
Mistral 7B V0.2 Bnb 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)
Mistral 7B V0.2 Bnb 4bit Parameters and Internals
| LLM Name | Mistral 7B V0.2 Bnb 4bit |
| Repository 🤗 | https://huggingface.co/unsloth/mistral-7b-v0.2-bnb-4bit |
| Model Size | 7b |
| Required VRAM | 4.1 GB |
| Updated | 2024-09-20 |
| Maintainer | unsloth |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Quantized Models of the Mistral 7B V0.2 Bnb 4bit
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Mistralbasket1 | 0 | 6 | 0 GB |
| ...istral RealworldQA V0.2 7B SFT | 1 | 67 | 14 GB |
| ...l RealworldQA V0.2 7B SFT GGUF | 1 | 15 | 7 GB |
| CompliAI FullModel1 GGUF | 0 | 20 | 5 GB |
| H4na 7B V0.1 Guff | 0 | 7 | 4 GB |
| ...al 7B Instruct Javascript 4bit | 0 | 9 | 4 GB |
| An4 7B GUFFv2.41 | 0 | 8 | 4 GB |
| An4 7B GUFFv2.4 | 0 | 7 | 4 GB |
| An4 7B GUFFv2.3 | 0 | 8 | 4 GB |
| An4 7B GUFFv2.1 | 0 | 8 | 4 GB |
Best Alternatives to Mistral 7B V0.2 Bnb 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...istral Nemo Base 2407 Bnb 4bit | 1000K / 8.3 GB | 11508 | 9 |
| ...al Nemo Instruct 2407 Bnb 4bit | 1000K / 8.3 GB | 55610 | 21 |
| ...t 3.5 0106 128K 8.0bpw H8 EXL2 | 128K / 7.4 GB | 6 | 1 |
| ...t 3.5 0106 128K 4.0bpw H6 EXL2 | 128K / 3.9 GB | 5 | 1 |
| Mistral 7B V0.3 Bnb 4bit | 32K / 4.1 GB | 24715 | 12 |
| Mistral 7B Instruct V0.2 4bit | 32K / 4.3 GB | 405 | 1 |
| Mistral 7B Instruct V0.2 Fp16 | 32K / 14.4 GB | 5 | 0 |
| ...tral 7B Instruct V0.3 Bnb 4bit | 32K / 4.1 GB | 62223 | 14 |
| ...tral 7B Instruct V0.2 Bnb 4bit | 32K / 4.1 GB | 15548 | 30 |
| Mistral V0.3 7B ORPO | 32K / 14.5 GB | 64 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/mistral-7b-v0.2-bnb-4bit .
Rank the Mistral 7B V0.2 Bnb 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? 36073 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803