metadata

language:
  - sv
  - da
  - 'no'
  - is
  - en
license: apache-2.0
tags:
  - merge
  - llama-cpp
  - gguf-my-repo
base_model:
  - timpal0l/Llama-3-8B-flashback-v1
  - cognitivecomputations/dolphin-2.9-llama3-8b
pipeline_tag: text-generation

NikolayKozloff/dolphin-2.9-llama3-8b-flashback-Q8_0-GGUF

This model was converted to GGUF format from timpal0l/dolphin-2.9-llama3-8b-flashback 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.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo NikolayKozloff/dolphin-2.9-llama3-8b-flashback-Q8_0-GGUF --model dolphin-2.9-llama3-8b-flashback.Q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo NikolayKozloff/dolphin-2.9-llama3-8b-flashback-Q8_0-GGUF --model dolphin-2.9-llama3-8b-flashback.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.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m dolphin-2.9-llama3-8b-flashback.Q8_0.gguf -n 128