second-state/Meta-Llama-3.1-8B-Instruct-GGUF
51.1k
<!-- 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 -->
Meta-Llama-3.1-8B-Instruct-GGUF
Original Model
meta-llama/Meta-Llama-3.1-8B-Instruct
Run with LlamaEdge
- LlamaEdge version: v0.16.5 and above
- Prompt template
- Prompt type for chat:
llama-3-chat
- Prompt string
<|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|>- Prompt type for tool use:
llama-3-tool
- Prompt string
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","unit"]}}}]
Question: {user_message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>- Context size:
128000
- Run as LlamaEdge service
- Chat
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-8B-Instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template llama-3-chat \
--ctx-size 128000 \
--model-name Llama-3.1-8b- Tool use
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-8B-Instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template llama-3-tool \
--ctx-size 128000 \
--model-name Llama-3.1-8b- Run as LlamaEdge command app
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-8B-Instruct-Q5_K_M.gguf \
llama-chat.wasm \
--prompt-template llama-3-chat \
--ctx-size 128000Quantized GGUF Models
Quantized with llama.cpp b4466.
