Triangle104/Valkyyrie-14b-v1-Q8_0-GGUF

This model was converted to GGUF format from aixonlab/Valkyyrie-14b-v1 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:

Valkyyrie 14b v1 is a fine-tuned large language model based on Microsoft's Phi-4, further trained to have better conversation capabilities.

Details 📊

Developed by: AIXON Lab
Model type: Causal Language Model
Language(s): English (primarily), may support other languages
License: apache-2.0
Repository: https://huggingface.co/aixonlab/Valkyyrie-14b-v1

Model Architecture 🏗️

Base model: phi-4
Parameter count: ~14 billion
Architecture specifics: Transformer-based language model

Training & Fine-tuning 🔄

Valkyyrie-14b-v1 was fine-tuned to achieve -

Better conversational skills
Better creativity for writing and conversations.
Broader knowledge across various topics
Improved performance on specific tasks like writing, analysis, and problem-solving
Better contextual understanding and response generation

Intended Use 🎯

As an assistant or specific role bot.

Ethical Considerations 🤔

As a fine-tuned model based on phi-4, this model may inherit biases and limitations from its parent model and the fine-tuning dataset. Users should be aware of potential biases in generated content and use the model responsibly.

---

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/Valkyyrie-14b-v1-Q8_0-GGUF --hf-file valkyyrie-14b-v1-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Valkyyrie-14b-v1-Q8_0-GGUF --hf-file valkyyrie-14b-v1-q8_0.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/Valkyyrie-14b-v1-Q8_0-GGUF --hf-file valkyyrie-14b-v1-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Valkyyrie-14b-v1-Q8_0-GGUF --hf-file valkyyrie-14b-v1-q8_0.gguf -c 2048