Instructions to use tencent/Hunyuan-MT-7B-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Hunyuan-MT-7B-fp8 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="tencent/Hunyuan-MT-7B-fp8")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tencent/Hunyuan-MT-7B-fp8") model = AutoModelForCausalLM.from_pretrained("tencent/Hunyuan-MT-7B-fp8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload generation_config.json with huggingface_hub
Browse files- generation_config.json +13 -0
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
127960,
|
| 5 |
+
127967
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 127961,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.55.0.dev0"
|
| 13 |
+
}
|