Update README.md

Adding Evaluation Results (#12)

Add link to ONNX format

Add link to GGUF format

Update model

Update README.md

Update inference examples

Update inference examples

Update inference examples

Update Recommended Inference Parameters

Update Recommended Inference Parameters

Update README.md

Update model

Update README.md

Adding Evaluation Results (#10)

Disable the inference widget as the model is still not working properly

Remove "stop" parameter from "inference" property, as it's not compatible with this model

Add missing "parameters" in "inference" property

Enable inference widget to check if it's working

Update examples in README to be compatible with soon-to-come ChatWidget (#9)

Set `sliding_window` to `1024`

Temporarily disable the inference widget

Add repetition_penalty to check if it solves the issue with inference in HuggingFace widget

For some reason the inference widget in HuggingFace started working differently, so I’m changing the params to check if it improves the results

Add 'Recommended Inference Parameters' section

Add `chat_template` to `tokenizer_config.json`

Update README.md

Update README.md

Upload added_tokens.json

Upload tokenizer.model

Update README.md

Update README.md

Update README.md

Update README.md

Delete tokenizer.model

Delete generation_config.json

Delete added_tokens.json

Update model

Add link to afrideva/TinyMistral-248M-SFT-v3-GGUF

Delete pytorch_model.bin

Adding `safetensors` variant of this model (#7)

Update model, now trined with OpenAssistant dataset in ChatML format (#6)

Update README.md

Update README.md

Update README.md

Remove the adapter from this repository (#4)

Update README.md

Delete pytorch_model.bin

Adding `safetensors` variant of this model (#2)

Update config.json