metadata

base_model: Locutusque/gpt2-xl-conversational
datasets:
  - Locutusque/InstructMix
language:
  - en
license: mit
metrics:
  - bleu
  - perplexity
  - loss
  - accuracy
pipeline_tag: text-generation
tags:
  - llama-cpp
  - gguf-my-repo
widget:
  - text: >-
      <|USER|> Design a Neo4j database and Cypher function snippet to Display
      Extreme Dental hygiene: Using Mouthwash for Analysis for Beginners.
      Implement if/else or switch/case statements to handle different conditions
      related to the Consent. Provide detailed comments explaining your control
      flow and the reasoning behind each decision. <|ASSISTANT|> 
  - text: '<|USER|> Write me a story about a magical place. <|ASSISTANT|> '
  - text: >-
      <|USER|> Write me an essay about the life of George Washington
      <|ASSISTANT|> 
  - text: '<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|> '
  - text: >-
      <|USER|> Craft me a list of some nice places to visit around the world.
      <|ASSISTANT|> 
  - text: >-
      <|USER|> How to manage a lazy employee: Address the employee verbally.
      Don't allow an employee's laziness or lack of enthusiasm to become a
      recurring issue. Tell the employee you're hoping to speak with them about
      workplace expectations and performance, and schedule a time to sit down
      together. Question: To manage a lazy employee, it is suggested to talk to
      the employee. True, False, or Neither? <|ASSISTANT|> 
inference:
  parameters:
    temperature: 0.8
    do_sample: true
    top_p: 0.14
    top_k: 41
    max_new_tokens: 250
    repetition_penalty: 1.176

antoste/gpt2-xl-conversational-Q4_K_M-GGUF

This model was converted to GGUF format from Locutusque/gpt2-xl-conversational 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 antoste/gpt2-xl-conversational-Q4_K_M-GGUF --hf-file gpt2-xl-conversational-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo antoste/gpt2-xl-conversational-Q4_K_M-GGUF --hf-file gpt2-xl-conversational-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 antoste/gpt2-xl-conversational-Q4_K_M-GGUF --hf-file gpt2-xl-conversational-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo antoste/gpt2-xl-conversational-Q4_K_M-GGUF --hf-file gpt2-xl-conversational-q4_k_m.gguf -c 2048