tommytracx's picture
Update README.md
8cc2b77 verified
|
raw
history blame
2.41 kB
metadata
base_model: GainEnergy/OGAI-8x7b
datasets:
  - GainEnergy/ogai-8x7B
  - GainEnergy/oilandgas-engineering-dataset
  - GainEnergy/ogdataset
  - GainEnergy/upstrimacentral
library_name: transformers
license: mit
tags:
  - oil-gas
  - drilling-engineering
  - mixtral-8x7b
  - lora
  - fine-tuned
  - energy-ai
  - retrieval-augmented-generation
  - llama-cpp
  - gguf-my-repo
model-index:
  - name: OGAI-8x7B
    results:
      - task:
          type: text-generation
          name: Drilling Engineering AI
        dataset:
          name: GainEnergy Oil & Gas Corpus
          type: custom
        metrics:
          - type: accuracy
            value: 94.8
            name: Drilling Calculations Accuracy
          - type: precision
            value: 91.2
            name: Engineering Document Retrieval Precision
          - type: contextual-coherence
            value: High
            name: Context Retention

GainEnergy/OGAI-8x7b-Q4_K_M-GGUF

This model was converted to GGUF format from GainEnergy/OGAI-8x7b using llama.cpp. Refer to the original model card for more details on the model.

Use with Ollama

Execute the following

ollama run hf.co/GainEnergy/OGAI-8x7b-Q4_K_M-GGUF:latest

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 GainEnergy/OGAI-8x7b-Q4_K_M-GGUF --hf-file ogai-8x7b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo GainEnergy/OGAI-8x7b-Q4_K_M-GGUF --hf-file ogai-8x7b-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 GainEnergy/OGAI-8x7b-Q4_K_M-GGUF --hf-file ogai-8x7b-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo GainEnergy/OGAI-8x7b-Q4_K_M-GGUF --hf-file ogai-8x7b-q4_k_m.gguf -c 2048