metadata

base_model: Nekochu/Llama-2-13B-German-ORPO
datasets:
  - mayflowergmbh/intel_orca_dpo_pairs_de
  - LeoLM/OpenSchnabeltier
  - LeoLM/German_Songs
  - LeoLM/German_Poems
  - bjoernp/ultrachat_de
  - mayflowergmbh/ultra-chat_de
  - mayflowergmbh/airoboros-3.0_de
  - mayflowergmbh/booksum_de
  - mayflowergmbh/dolphin_de
  - mayflowergmbh/evol-instruct_de
  - mayflowergmbh/openschnabeltier_de
  - mayflowergmbh/alpaca-gpt4_de
  - mayflowergmbh/dolly-15k_de
  - mayflowergmbh/oasst_de
language:
  - de
  - en
library_name: peft
license: apache-2.0
pipeline_tag: text-generation
tags:
  - llama-factory
  - lora
  - generated_from_trainer
  - llama2
  - llama
  - instruct
  - finetune
  - llm
  - pytorch
  - llama-2
  - german
  - deutsch
  - llama-cpp
  - gguf-my-repo
model_creator: Nekochu
quantized_by: Nekochu
pretty_name: Llama-2 13B German ORPO
model_type: llama2
prompt_template: >-
  Below is an instruction that describes a task. Write a response that
  appropriately completes the request. ### Instruction: {Instruction} {summary}
  ### input: {category} ### Response: {prompt}
task_categories:
  - question-answering
  - text2text-generation
  - conversational
inference: true
model-index:
  - name: Llama-2-13B-German-ORPO
    results: []

jott1970/Llama-2-13B-German-ORPO-Q4_K_M-GGUF

This model was converted to GGUF format from Nekochu/Llama-2-13B-German-ORPO 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 jott1970/Llama-2-13B-German-ORPO-Q4_K_M-GGUF --hf-file llama-2-13b-german-orpo-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo jott1970/Llama-2-13B-German-ORPO-Q4_K_M-GGUF --hf-file llama-2-13b-german-orpo-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 jott1970/Llama-2-13B-German-ORPO-Q4_K_M-GGUF --hf-file llama-2-13b-german-orpo-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo jott1970/Llama-2-13B-German-ORPO-Q4_K_M-GGUF --hf-file llama-2-13b-german-orpo-q4_k_m.gguf -c 2048