Question Answering
Transformers
PyTorch
TensorBoard
Safetensors
qwen2
text-generation
unsloth
trl
sft
text-generation-inference
Instructions to use vignesha7/DeepSeek-R1-Distill-Qwen-7B-Financial-Expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vignesha7/DeepSeek-R1-Distill-Qwen-7B-Financial-Expert with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" 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("question-answering", model="vignesha7/DeepSeek-R1-Distill-Qwen-7B-Financial-Expert")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("vignesha7/DeepSeek-R1-Distill-Qwen-7B-Financial-Expert") model = AutoModelForCausalLM.from_pretrained("vignesha7/DeepSeek-R1-Distill-Qwen-7B-Financial-Expert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -188,7 +188,7 @@
|
|
| 188 |
"legacy": true,
|
| 189 |
"model_max_length": 131072,
|
| 190 |
"pad_token": "<|vision_pad|>",
|
| 191 |
-
"padding_side": "
|
| 192 |
"sp_model_kwargs": {},
|
| 193 |
"tokenizer_class": "LlamaTokenizerFast",
|
| 194 |
"unk_token": null,
|
|
|
|
| 188 |
"legacy": true,
|
| 189 |
"model_max_length": 131072,
|
| 190 |
"pad_token": "<|vision_pad|>",
|
| 191 |
+
"padding_side": "left",
|
| 192 |
"sp_model_kwargs": {},
|
| 193 |
"tokenizer_class": "LlamaTokenizerFast",
|
| 194 |
"unk_token": null,
|