Instructions to use MERaLiON/MERaLiON-2-10B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MERaLiON/MERaLiON-2-10B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="MERaLiON/MERaLiON-2-10B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("MERaLiON/MERaLiON-2-10B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update vllm_plugin_meralion2/openai_client_curl.sh
Browse files
vllm_plugin_meralion2/openai_client_curl.sh
CHANGED
|
@@ -13,7 +13,7 @@ curl http://localhost:8000/v1/chat/completions \
|
|
| 13 |
"max_completion_tokens": 1024,
|
| 14 |
"temperature": 0.0,
|
| 15 |
"top_p": 0.9,
|
| 16 |
-
"repetition_penalty": 1.
|
| 17 |
"top_k": 50,
|
| 18 |
"length_penalty": 1.0,
|
| 19 |
"logits_processors": [{"qualname": "vllm_plugin_meralion2.NoRepeatNGramLogitsProcessor", "args": []}],
|
|
|
|
| 13 |
"max_completion_tokens": 1024,
|
| 14 |
"temperature": 0.0,
|
| 15 |
"top_p": 0.9,
|
| 16 |
+
"repetition_penalty": 1.05,
|
| 17 |
"top_k": 50,
|
| 18 |
"length_penalty": 1.0,
|
| 19 |
"logits_processors": [{"qualname": "vllm_plugin_meralion2.NoRepeatNGramLogitsProcessor", "args": []}],
|