This model was converted to GGUF format from addansee/Qwen1.5-1.8B-Chat-heretic using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Chat Template

jinja

{%- for message in messages -%}
	{%- if loop.first and messages[0]["role"] != "system" -%}
		{{- "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n" -}}
	{%- endif -%}
	{{- "<|im_start|>" + message["role"] + "\n" + message["content"] + "<|im_end|>" + "\n" -}}
{%- endfor -%}
{%- if add_generation_prompt -%}
	{{- "<|im_start|>assistant\n" -}}
{%- endif -%}

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

bash

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo PJRM/Qwen1.5-1.8B-Chat-heretic-Q4_K_M-GGUF --hf-file qwen1.5-1.8b-chat-heretic-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo PJRM/Qwen1.5-1.8B-Chat-heretic-Q4_K_M-GGUF --hf-file qwen1.5-1.8b-chat-heretic-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 PJRM/Qwen1.5-1.8B-Chat-heretic-Q4_K_M-GGUF --hf-file qwen1.5-1.8b-chat-heretic-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo PJRM/Qwen1.5-1.8B-Chat-heretic-Q4_K_M-GGUF --hf-file qwen1.5-1.8b-chat-heretic-q4_k_m.gguf -c 2048