---

base_model: Roxwell/NEMO-12B-SFT-Further

tags:

• text-generation-inference USE TEMPERATURE OF 0.85 or 0.9 FOR BEST RESULTS
• transformers
• unsloth
• mistral
• llama-cpp
• gguf-my-repo
• Use Temperature of 0.85

license: apache-2.0

language:

• en

--- THIS IS A FINE TUNED LLM of NEMO 12B on Business and Fraud Detection. The Tone is Professional and replies in a good polite way.

--- THE TONE IS VERY PROFESSIONAL AND SOFT. I've trained it to read Business LAW. IF a business RAG is used, it talks about specific Regulations.

Roxwell/NEMO-12B-SFT-Further-Q4_K_M-GGUF

This model was converted to GGUF format from Roxwell/NEMO-12B-SFT-Further using llama.cpp via the ggml.ai's GGUF-my-repo space.

Refer to the original model card for more details on the model.

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 Roxwell/NEMO-12B-SFT-Further-Q4_K_M-GGUF --hf-file nemo-12b-sft-further-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Roxwell/NEMO-12B-SFT-Further-Q4_K_M-GGUF --hf-file nemo-12b-sft-further-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 Roxwell/NEMO-12B-SFT-Further-Q4_K_M-GGUF --hf-file nemo-12b-sft-further-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Roxwell/NEMO-12B-SFT-Further-Q4_K_M-GGUF --hf-file nemo-12b-sft-further-q4_k_m.gguf -c 2048