Edit model card

cstr/aya-expanse-8b-Q4_K_M-GGUF

This model was converted to GGUF format from CohereForAI/aya-expanse-8b 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 cstr/aya-expanse-8b-Q4_K_M-GGUF --hf-file aya-expanse-8b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo cstr/aya-expanse-8b-Q4_K_M-GGUF --hf-file aya-expanse-8b-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 cstr/aya-expanse-8b-Q4_K_M-GGUF --hf-file aya-expanse-8b-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo cstr/aya-expanse-8b-Q4_K_M-GGUF --hf-file aya-expanse-8b-q4_k_m.gguf -c 2048

ollama

use a modelfile like:

FROM aya-expanse-8b-q4_k_m.gguf
TEMPLATE "{{ if .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ .System }}<|END_OF_TURN_TOKEN|>
{{ end }}{{ if .Prompt }}<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ .Prompt }}<|END_OF_TURN_TOKEN|>
{{ end }}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>"

PARAMETER num_ctx 8192
PARAMETER stop "<|END_OF_TURN_TOKEN|>"
PARAMETER stop "<|START_OF_TURN_TOKEN|>"
PARAMETER stop "|END_OF_TURN_TOKEN"
PARAMETER stop "|START_OF_TURN_TOKEN"

SYSTEM "You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Cohere For AI."
Downloads last month
313
GGUF
Model size
8.03B params
Architecture
command-r

4-bit

Inference API
Inference API (serverless) has been turned off for this model.

Model tree for cstr/aya-expanse-8b-Q4_K_M-GGUF

Quantized
(20)
this model