Triangle104/Llama-3.1-8B-UltraLong-4M-Instruct-Q4_K_M-GGUF

This model was converted to GGUF format from nvidia/Llama-3.1-8B-UltraLong-4M-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.

---

We introduce UltraLong-8B, a series of ultra-long context language models designed to process extensive sequences of text (up to 1M, 2M, and 4M tokens) while maintaining competitive performance on standard benchmarks. Built on the Llama-3.1, UltraLong-8B leverages a systematic training recipe that combines efficient continued pretraining with instruction tuning to enhance long-context understanding and instruction-following capabilities. This approach enables our models to efficiently scale their context windows without sacrificing general performance.

---

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-3.1-8B-UltraLong-4M-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-ultralong-4m-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Llama-3.1-8B-UltraLong-4M-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-ultralong-4m-instruct-q4_k_m.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-3.1-8B-UltraLong-4M-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-ultralong-4m-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Llama-3.1-8B-UltraLong-4M-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-ultralong-4m-instruct-q4_k_m.gguf -c 2048