Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Lora Mistral Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/nuebaek/mistral_mss_b_2jh
Mistral Mss B 2jh 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 Mss B 2jh Parameters and Internals
| LLM Name | Mistral Mss B 2jh |
| Repository 🤗 | https://huggingface.co/nuebaek/mistral_mss_b_2jh |
| Model Size | 3.9b |
| Required VRAM | 4.7 GB |
| Updated | 2025-02-22 |
| Maintainer | nuebaek |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 1024 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|down_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 8 |
Best Alternatives to Mistral Mss B 2jh
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Draft Mistral Ft Mss | 0K / 4.7 GB | 14 | 0 |
| Komt Mistral Smilestyle | 0K / 4.7 GB | 77 | 0 |
| Assistant Chatbot Mistral | 0K / 5.3 GB | 5 | 1 |
| Bamboo Llm | 0K / 0.1 GB | 336 | 13 |
Note: green Score (e.g. "73.2") means that the model is better than nuebaek/mistral_mss_b_2jh .
Rank the Mistral Mss B 2jh 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227