Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Prompt template:

[INST] Corrects and rephrase user text grammar errors delimited by triple backticks to standard English.
### Input: Text=\`\`\`she no went to market\`\`\` [/INST]
[INST] ### Output: She didnโ€™t go the market. [/INST]
[INST] ### Input: Text=\`\`\`${input}\`\`\` [/INST]
[INST] ### Output:

To use the fine-tuned model, you need to get a downloadable link for the model from HF and update it accordingly in the shell script. For example:

MODEL_URL="https://huggingface.co/mzbac/mistral-grammar/resolve/main/Mistral-7B-Grammar-Correaction-v1.1.3.Q5_K_M.gguf"
MODEL_FILE="Mistral-7B-Grammar-Correaction-v1.1.3.Q5_K_M.gguf"

For details on how to use the model with Mac Automator, please check out the article here.

Downloads last month
159
GGUF
Model size
7.24B params
Architecture
llama

5-bit

Inference API
Unable to determine this model's library. Check the docs .

Space using mzbac/mistral-grammar 1