Multiple Choice
Transformers
Safetensors
qwen3
text-generation
qlora
quantization
4bit
causal-lm
mcqa
dpo
w4a16
hf-trained
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use abdou-u/MNLP_M3_quantized_dpo_mcqa_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdou-u/MNLP_M3_quantized_dpo_mcqa_model with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("abdou-u/MNLP_M3_quantized_dpo_mcqa_model") model = AutoModelForCausalLM.from_pretrained("abdou-u/MNLP_M3_quantized_dpo_mcqa_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "pad_token_id": 151643, | |
| "transformers_version": "4.52.4", | |
| "use_cache": false | |
| } | |