second-state/Octopus-v2-GGUF

---

Octopus-v2-2B-GGUF

Original Model

NexaAIDev/Octopus-v2

Run with LlamaEdge

• LlamaEdge version: v0.8.1 and above

  • Prompt template

    • Prompt type: octopus

    • Prompt string

      {system_prompt}\n\nQuery: {input_text} \n\nResponse:
      

• Context size: 2048

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Octopus-v2-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template octopus \
    --ctx-size 2048 \
    --model-name octopus-v2
  

  Example of a user request in json format:

  {
      "messages": [
          {
              "role": "system",
              "content": "Below is the query from the users, please call the correct function and generate the parameters to call the function."
          },
          {
              "role": "user",
              "content": "Take a selfie for me with front camera"
          }
      ],
      "model": "octopus-v2",
      "stream": false
  }
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Octopus-v2-Q2_K.gguf	Q2_K	2	1.16 GB	smallest, significant quality loss - not recommended for most purposes
Octopus-v2-Q3_K_L.gguf	Q3_K_L	3	1.47 GB	small, substantial quality loss
Octopus-v2-Q3_K_M.gguf	Q3_K_M	3	1.38 GB	very small, high quality loss
Octopus-v2-Q3_K_S.gguf	Q3_K_S	3	1.29 GB	very small, high quality loss
Octopus-v2-Q4_0.gguf	Q4_0	4	1.55 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Octopus-v2-Q4_K_M.gguf	Q4_K_M	4	1.63 GB	medium, balanced quality - recommended
Octopus-v2-Q4_K_S.gguf	Q4_K_S	4	1.56 GB	small, greater quality loss
Octopus-v2-Q5_0.gguf	Q5_0	5	1.8 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Octopus-v2-Q5_K_M.gguf	Q5_K_M	5	1.84 GB	large, very low quality loss - recommended
Octopus-v2-Q5_K_S.gguf	Q5_K_S	5	1.8 GB	large, low quality loss - recommended
Octopus-v2-Q6_K.gguf	Q6_K	6	2.06 GB	very large, extremely low quality loss
Octopus-v2-Q8_0.gguf	Q8_0	8	2.67 GB	very large, extremely low quality loss - not recommended
Octopus-v2-f16.gguf	f16	16	10 GB

Quantized with llama.cpp b2589