Triangle104/Llama-Sentient-3.2-3B-Instruct-Q6_K-GGUF

This model was converted to GGUF format from prithivMLmods/Llama-Sentient-3.2-3B-Instruct using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Model details:

The Llama-Sentient-3.2-3B-Instruct model is a fine-tuned version of the Llama-3.2-3B-Instruct model, optimized for text generation tasks, particularly where instruction-following abilities are critical. This model is trained on the mlabonne/lmsys-arena-human-preference-55k-sharegpt dataset, which enhances its performance in conversational and advisory contexts, making it suitable for a wide range of applications. Key Use Cases:

Conversational AI: Engage in intelligent dialogue, offering coherent responses and following instructions, useful for customer support and virtual assistants. Text Generation: Generate high-quality, contextually appropriate content such as articles, summaries, explanations, and other forms of written communication based on user prompts. Instruction Following: Follow specific instructions with accuracy, making it ideal for tasks that require structured guidance, such as technical troubleshooting or educational assistance.

The model uses a PyTorch-based architecture and includes a range of necessary files such as configuration files, tokenizer files, and model weight files for deployment.

    Intended Applications:

Chatbots for virtual assistance, customer support, or as personal digital assistants. Content Creation Tools, aiding in the generation of written materials, blog posts, or automated responses based on user inputs. Educational and Training Systems, providing explanations and guided learning experiences in various domains. Human-AI Interaction platforms, where the model can follow user instructions to provide personalized assistance or perform specific tasks.

With its strong foundation in instruction-following and conversational contexts, the Llama-Sentient-3.2-3B-Instruct model offers versatile applications for both general and specialized domains.

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Llama-Sentient-3.2-3B-Instruct-Q6_K-GGUF --hf-file llama-sentient-3.2-3b-instruct-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Llama-Sentient-3.2-3B-Instruct-Q6_K-GGUF --hf-file llama-sentient-3.2-3b-instruct-q6_k.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/Llama-Sentient-3.2-3B-Instruct-Q6_K-GGUF --hf-file llama-sentient-3.2-3b-instruct-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Llama-Sentient-3.2-3B-Instruct-Q6_K-GGUF --hf-file llama-sentient-3.2-3b-instruct-q6_k.gguf -c 2048