Instructions to use HuggingFaceTB/smollm-360M-instruct-add-basics-q0f16-MLC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLC-LLM
How to use HuggingFaceTB/smollm-360M-instruct-add-basics-q0f16-MLC with MLC-LLM:
# 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
Update mlc-chat-config.json (#1)
Browse files- Update mlc-chat-config.json (4f9109bb7f74c14a394a61076cdf9b28554856e1)
- mlc-chat-config.json +2 -2
mlc-chat-config.json
CHANGED
|
@@ -27,11 +27,11 @@
|
|
| 27 |
"attention_sink_size": -1,
|
| 28 |
"tensor_parallel_shards": 1,
|
| 29 |
"pipeline_parallel_stages": 1,
|
| 30 |
-
"temperature":
|
| 31 |
"presence_penalty": 0.0,
|
| 32 |
"frequency_penalty": 0.0,
|
| 33 |
"repetition_penalty": 1.0,
|
| 34 |
-
"top_p":
|
| 35 |
"tokenizer_files": [
|
| 36 |
"tokenizer.json",
|
| 37 |
"vocab.json",
|
|
|
|
| 27 |
"attention_sink_size": -1,
|
| 28 |
"tensor_parallel_shards": 1,
|
| 29 |
"pipeline_parallel_stages": 1,
|
| 30 |
+
"temperature": 0.9,
|
| 31 |
"presence_penalty": 0.0,
|
| 32 |
"frequency_penalty": 0.0,
|
| 33 |
"repetition_penalty": 1.0,
|
| 34 |
+
"top_p": 0.2,
|
| 35 |
"tokenizer_files": [
|
| 36 |
"tokenizer.json",
|
| 37 |
"vocab.json",
|