4bit Base model:quantized:unsloth/m... Base model:unsloth/mistral-7b-... En Endpoints compatible Gguf Instruct Lora Mistral Pytorch Quantized Region:us Safetensors Sft Sharded Trl Unsloth
Mistral 7B Instruct V0.2 Python 18K Parameters and Internals
| LLM Name | Mistral 7B Instruct V0.2 Python 18K |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2024-07-26 |
| Maintainer | theprint |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | 4bit|gguf |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|gate_proj|o_proj|up_proj|q_proj|down_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Mistral 7B Instruct V0.2 Python 18K
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Pixel | 0.3 | 8K / 4.4 GB | 81 | 0 |
| Mistral 7B Instruct V0.3 GGUF | 0.4 | 0K / 1.6 GB | 192317 | 51 |
| Calme 2.2 Qwen2 7B GGUF | 0.3 | 0K / 4.5 GB | 19589 | 1 |
| Calme 2.1 Qwen2 7B GGUF | 0.3 | 0K / 4.5 GB | 19069 | 0 |
| Calme 2.6 Qwen2 7B GGUF | 0.3 | 0K / 4.5 GB | 13592 | 1 |
| Mistral 7B Instruct V0.3 GGUF | 0.3 | 0K / 2.7 GB | 59058 | 2 |
| Qwen2 7B Instruct V0.6 GGUF | 0.3 | 0K / 4.5 GB | 13522 | 0 |
| Calme 2.3 Qwen2 7B GGUF | 0.3 | 0K / 4.5 GB | 8978 | 2 |
| Calme 2.7 Qwen2 7B GGUF | 0.3 | 0K / 4.5 GB | 9625 | 1 |
| Qwen2 7B Instruct V0.3 GGUF | 0.3 | 0K / 4.5 GB | 8911 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than theprint/Mistral-7b-Instruct-v0.2-python-18k .
Rank the Mistral 7B Instruct V0.2 Python 18K 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501