Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Llama Lora Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/henilp105/InjecAgent-llama-7b-optim
InjecAgent Llama 7B Optim 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)
InjecAgent Llama 7B Optim Parameters and Internals
| LLM Name | InjecAgent Llama 7B Optim |
| Repository 🤗 | https://huggingface.co/henilp105/InjecAgent-llama-7b-optim |
| Model Size | 7b |
| Required VRAM | 0.6 GB |
| Updated | 2025-09-10 |
| Maintainer | henilp105 |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj|lm_head|o_proj|k_proj|gate_proj|down_proj|up_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
Best Alternatives to InjecAgent Llama 7B Optim
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B V0.3 | 32K / 14.5 GB | 1289 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 25 | 5 |
| ...unoichi Lemon Royale V3 32K 7B | 32K / 14.5 GB | 7 | 5 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 731 | 3 |
| Mistralai Mistral 7B V0.3 | 32K / 14.5 GB | 59 | 3 |
| ...ralai Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 35 | 2 |
| Mistral 7B Instruct V0.3 | 32K / 14.5 GB | 8 | 0 |
| Mistral 7B V0.2 | 32K / 14.5 GB | 8 | 1 |
| Full V4 Astromistral Final | 32K / 4.5 GB | 3 | 1 |
| LlamaGuard 7B | 4K / 13.5 GB | 9513 | 239 |
Note: green Score (e.g. "73.2") means that the model is better than henilp105/InjecAgent-llama-7b-optim .
Rank the InjecAgent Llama 7B Optim 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? 51262 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124