Instructions to use leafiy/mia-laya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use leafiy/mia-laya with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download final/rl_agent_config.json from leafiy/mia-laya: direct link, hf CLI and curl.
- Browser
- Download file 960 Bytes
-
https://huggingface.co/leafiy/mia-laya/resolve/main/final/rl_agent_config.json
- Command line
-
hf download hf://leafiy/mia-laya/final/rl_agent_config.json
-
curl -L -o rl_agent_config.json https://huggingface.co/leafiy/mia-laya/resolve/main/final/rl_agent_config.json
960 Bytes
| { | |
| "encoder": "jhu-clsp/mmBERT-base", | |
| "head_layers": 2, | |
| "max_len": 512, | |
| "head_max_len": 256, | |
| "max_prefixes": 6, | |
| "act_costs": { | |
| "escalate": 0.5 | |
| }, | |
| "cost_wrong_act": 3.0, | |
| "amp_dtype": "bf16", | |
| "model_name": "rl-agent", | |
| "temperature": [ | |
| 1.9487578187426935, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "temperature_by_options": { | |
| "choice:3-5": 1.9487578187426935 | |
| }, | |
| "training": { | |
| "objective": "supervised_cross_entropy", | |
| "epochs_completed": 3, | |
| "updates": 852, | |
| "fine_tuned_from_checkpoint": true | |
| }, | |
| "sentiment_labels": [ | |
| "负面", | |
| "中性", | |
| "正面" | |
| ], | |
| "sentiment_question": { | |
| "sentiment": { | |
| "type": "choice", | |
| "instructions": "判断文本表达的整体情感倾向。", | |
| "criteria": { | |
| "负面": "表达不满、失望、批评等负面态度", | |
| "中性": "态度客观或情绪不明显", | |
| "正面": "表达满意、赞赏、愉快等正面态度" | |
| } | |
| } | |
| } | |
| } | |