Instructions to use legraphista/Reflection-Llama-3.1-70B-IMat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use legraphista/Reflection-Llama-3.1-70B-IMat-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

Use Docker

docker model run hf.co/legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

LM Studio
Jan

vLLM

How to use legraphista/Reflection-Llama-3.1-70B-IMat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "legraphista/Reflection-Llama-3.1-70B-IMat-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "legraphista/Reflection-Llama-3.1-70B-IMat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

Ollama
How to use legraphista/Reflection-Llama-3.1-70B-IMat-GGUF with Ollama:
```
ollama run hf.co/legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S
```
Unsloth Desktop
Docker Model Runner
How to use legraphista/Reflection-Llama-3.1-70B-IMat-GGUF with Docker Model Runner:
```
docker model run hf.co/legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S
```

Lemonade

How to use legraphista/Reflection-Llama-3.1-70B-IMat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull legraphista/Reflection-Llama-3.1-70B-IMat-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.Reflection-Llama-3.1-70B-IMat-GGUF-Q4_K_S

List all available models

lemonade list

Atomic Chat

legraphista commited on Sep 6, 2024

Commit

7e0eb2a

verified ·

1 Parent(s): 65d0406

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -11

README.md CHANGED Viewed

@@ -36,7 +36,6 @@ IMatrix dataset: [here](https://gist.githubusercontent.com/bartowski1182/eb213dc
     - [All Quants](#all-quants)
 - [Downloading using huggingface-cli](#downloading-using-huggingface-cli)
 - [Inference](#inference)
-    - [Simple chat template](#simple-chat-template)
     - [Chat template with system prompt](#chat-template-with-system-prompt)
     - [Llama.cpp](#llama-cpp)
 - [FAQ](#faq)
@@ -110,16 +109,9 @@ huggingface-cli download legraphista/Reflection-Llama-3.1-70B-IMat-GGUF --includ
 ## Inference
-### Simple chat template
-```
-<|begin_of_text|><|start_header_id|>user<|end_header_id|>
-{user_prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-{assistant_response}<|eot_id|><|start_header_id|>user<|end_header_id|>
-{next_user_prompt}<|eot_id|>
-```
 ### Chat template with system prompt
 ```

     - [All Quants](#all-quants)
 - [Downloading using huggingface-cli](#downloading-using-huggingface-cli)
 - [Inference](#inference)
     - [Chat template with system prompt](#chat-template-with-system-prompt)
     - [Llama.cpp](#llama-cpp)
 - [FAQ](#faq)
 ## Inference
+> [!IMPORTANT]
+> Make sure to set the system prompt:
+> `You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.`
 ### Chat template with system prompt
 ```