Arxiv:1910.09700 Adapter Base model:adapter:thebloke/ll... Base model:thebloke/llama-2-7b... Endpoints compatible Finetuned Fp16 Gguf Lora Peft Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Userb1az/llama2-7b-tuned
Llama2 7B Tuned 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)
Llama2 7B Tuned Parameters and Internals
| LLM Name | Llama2 7B Tuned |
| Repository 🤗 | https://huggingface.co/Userb1az/llama2-7b-tuned |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.1 GB |
| Updated | 2025-02-13 |
| Maintainer | Userb1az |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | fp16|gguf |
| Model Architecture | Adapter |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|v_proj|q_proj|o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Llama2 7B Tuned
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Lemonilia ShoriRP V0.75d | 0K / 0.2 GB | 10 | 1 |
| ... Instruct Mistral 7B V0.1.gguf | 0K / 0 GB | 24 | 1 |
| Mistral Chess | 0K / 2.7 GB | 27 | 0 |
| Atomgpt Mistral Tc Supercon | 0K / 0.2 GB | 30 | 3 |
| ...hat Hf Hotel Booking Assistant | 0K / 0.2 GB | 8 | 0 |
| Mistral Numericnlg FV | 0K / 0.3 GB | 6 | 0 |
| Mistral Wikitable FV | 0K / 0.3 GB | 8 | 0 |
| Mistral Charttotext FV | 0K / 0.3 GB | 5 | 0 |
| Gemma 7B Us Minecraft | 0K / 0 GB | 117 | 0 |
| Gemma7b SFT | 0K / 0 GB | 20 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Userb1az/llama2-7b-tuned .
Rank the Llama2 7B Tuned 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