Autotrain compatible Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/tomaszki/mistral-7
Mistral 7 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 7 Parameters and Internals
| LLM Name | Mistral 7 |
| Repository 🤗 | https://huggingface.co/tomaszki/mistral-7 |
| Model Size | 7.2b |
| Required VRAM | 14.4 GB |
| Updated | 2025-03-14 |
| Maintainer | tomaszki |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mistral 7
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saka 7.2B | 195K / 14.6 GB | 13 | 0 |
| XxxI Ixxx | 32K / 14.4 GB | 36 | 0 |
| Test01 | 32K / 14.4 GB | 4 | 1 |
| Nous Hermes 2 Mixtral 8x7B DPO | 32K / 14.4 GB | 16 | 1 |
| Sn6 10 | 32K / 14.4 GB | 10 | 1 |
| Nousaimodeltao | 32K / 14.4 GB | 14 | 1 |
| Nous Thirty | 32K / 14.4 GB | 14 | 1 |
| Weeeeee.1 | 32K / 14.4 GB | 41 | 1 |
| Nous Nous V1 | 32K / 14.4 GB | 13 | 0 |
| Test1 | 32K / 14.4 GB | 12 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than tomaszki/mistral-7 .
Rank the Mistral 7 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? 45019 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227