---
license: cc-by-nc-4.0
model_name: xLAM-8x22b-r
base_model: Salesforce/xLAM-8x22b-r
inference: false
model_creator: MediaTek-Research
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
- en
tags:
- function-calling
- LLM Agent
- tool-use
- mistral
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# xLAM-8x22b-r-GGUF

## Original Model

[Salesforce/xLAM-8x22b-r](https://huggingface.co/Salesforce/xLAM-8x22b-r)

## Run with LlamaEdge

- LlamaEdge version: coming soon

<!-- - LlamaEdge version: [v0.14.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.0) and above

- Prompt template

  - Prompt type: `llama-3-chat`

  - Prompt string

    ```text
    <|begin_of_text|><|start_header_id|>system<|end_header_id|>

    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    ```

- Context size: `64000`

- Run as LlamaEdge service

  - Chat

    ```bash
    wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-8x22b-r-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template llama-3-chat \
      --ctx-size 128000 \
      --model-name Llama-3.1-8b
    ```

  - Tool use

    ```bash
    wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-8x22b-r-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template llama-3-tool \
      --ctx-size 64000 \
      --model-name Llama-3.1-8b
    ```

- Run as LlamaEdge command app

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-8x22b-r-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 64000
  ``` -->

*Quantized with llama.cpp b3613*