Version 2024-09-19: based on mistralai/Mistral-Small-Instruct-2409 commit 63e53df6575e7085d62113f4383835ff979b3795 mistralai commit history

For LM Studio 0.3.2 change the tokenizer.chat_template in Advanded Configuration/Prompt Template/Jinja and use the old one :

{%- if messages[0]['role'] == 'system' %} {%- set system_message = messages[0]['content'] %} {%- set loop_messages = messages[1:] %} {%- else %} {%- set loop_messages = messages %} {%- endif %} {{- bos_token }} {%- for message in loop_messages %} {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %} {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }} {%- endif %} {%- if message['role'] == 'user' %} {%- if loop.first and system_message is defined %} {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }} {%- else %} {{- ' [INST] ' + message['content'] + ' [/INST]' }} {%- endif %} {%- elif message['role'] == 'assistant' %} {{- ' ' + message['content'] + eos_token}} {%- else %} {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }} {%- endif %} {%- endfor %}

hrus/Mistral-Small-Instruct-2409-Q6_K-GGUF

This model was converted to GGUF format from mistralai/Mistral-Small-Instruct-2409 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

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

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo hrus/Mistral-Small-Instruct-2409-Q6_K-GGUF --hf-file mistral-small-instruct-2409-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo hrus/Mistral-Small-Instruct-2409-Q6_K-GGUF --hf-file mistral-small-instruct-2409-q6_k.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 hrus/Mistral-Small-Instruct-2409-Q6_K-GGUF --hf-file mistral-small-instruct-2409-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo hrus/Mistral-Small-Instruct-2409-Q6_K-GGUF --hf-file mistral-small-instruct-2409-q6_k.gguf -c 2048