4bit Base model:finetune:unsloth/mi... Base model:unsloth/mistral-7b-... Dataset:shivam9980/cnn-english... En Endpoints compatible Instruct Lora Mistral Model-index Quantized Region:us Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/shivam9980/mistral-7b-news-cnn-merged
Mistral 7B News Cnn Merged Benchmarks
MMLU Pro: 20.31
GPQA: 7.83
MUSR: 15.67
BBH: 11.15
IFEval: 46.34 vs 88 (so35)-47.3%
MATH Lvl 5: 1.44
LLME Score: 0.22976
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 News Cnn Merged Parameters and Internals
| LLM Name | Mistral 7B News Cnn Merged |
| Repository 🤗 | https://huggingface.co/shivam9980/mistral-7b-news-cnn-merged |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.3 GB |
| Updated | 2024-12-22 |
| Maintainer | shivam9980 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|o_proj|gate_proj|v_proj|k_proj|up_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to Mistral 7B News Cnn Merged
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen 2.1 7B Persona Lora Model | 0K / 0.2 GB | 0 | 1 |
| Qwen2.5 7B Exp2 Lora Model | 0K / 0.2 GB | 0 | 1 |
| Qwen 2.5 7B Rp Lora | 0K / 0.2 GB | 0 | 1 |
| Pixel | 8K / 4.4 GB | 19 | 0 |
| ... 7b 448 Qinstruct Preview V0.1 | 2K / 17.3 GB | 17 | 4 |
| Mistral 7B Instruct V0.3 GGUF | 0K / 1.6 GB | 2034820 | 68 |
| Qwen2 7B Instruct GGUF | 0K / 1.9 GB | 1971571 | 10 |
| Qwen UMLS 7B Instruct GGUF | 0K / 4.7 GB | 991 | 8 |
| QwQ LCoT 7B Instruct GGUF | 0K / 4.7 GB | 347 | 7 |
| Neumind Math 7B Instruct GGUF | 0K / 4.7 GB | 158 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than shivam9980/mistral-7b-news-cnn-merged .
Rank the Mistral 7B News Cnn Merged 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217