Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) lambda-qwen2.5-14b-dpo-test - GGUF - Model creator: https://huggingface.co/tanliboy/ - Original model: https://huggingface.co/tanliboy/lambda-qwen2.5-14b-dpo-test/ | Name | Quant method | Size | | ---- | ---- | ---- | | [lambda-qwen2.5-14b-dpo-test.Q2_K.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q2_K.gguf) | Q2_K | 5.37GB | | [lambda-qwen2.5-14b-dpo-test.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.IQ3_XS.gguf) | IQ3_XS | 5.94GB | | [lambda-qwen2.5-14b-dpo-test.IQ3_S.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.IQ3_S.gguf) | IQ3_S | 6.23GB | | [lambda-qwen2.5-14b-dpo-test.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q3_K_S.gguf) | Q3_K_S | 6.2GB | | [lambda-qwen2.5-14b-dpo-test.IQ3_M.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.IQ3_M.gguf) | IQ3_M | 6.44GB | | [lambda-qwen2.5-14b-dpo-test.Q3_K.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q3_K.gguf) | Q3_K | 6.84GB | | [lambda-qwen2.5-14b-dpo-test.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q3_K_M.gguf) | Q3_K_M | 6.84GB | | [lambda-qwen2.5-14b-dpo-test.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q3_K_L.gguf) | Q3_K_L | 7.38GB | | [lambda-qwen2.5-14b-dpo-test.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.IQ4_XS.gguf) | IQ4_XS | 7.62GB | | [lambda-qwen2.5-14b-dpo-test.Q4_0.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q4_0.gguf) | Q4_0 | 7.93GB | | [lambda-qwen2.5-14b-dpo-test.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.IQ4_NL.gguf) | IQ4_NL | 8.01GB | | [lambda-qwen2.5-14b-dpo-test.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q4_K_S.gguf) | Q4_K_S | 7.98GB | | [lambda-qwen2.5-14b-dpo-test.Q4_K.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q4_K.gguf) | Q4_K | 8.37GB | | [lambda-qwen2.5-14b-dpo-test.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q4_K_M.gguf) | Q4_K_M | 8.37GB | | [lambda-qwen2.5-14b-dpo-test.Q4_1.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q4_1.gguf) | Q4_1 | 8.75GB | | [lambda-qwen2.5-14b-dpo-test.Q5_0.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q5_0.gguf) | Q5_0 | 9.56GB | | [lambda-qwen2.5-14b-dpo-test.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q5_K_S.gguf) | Q5_K_S | 9.56GB | | [lambda-qwen2.5-14b-dpo-test.Q5_K.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q5_K.gguf) | Q5_K | 9.79GB | | [lambda-qwen2.5-14b-dpo-test.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q5_K_M.gguf) | Q5_K_M | 9.79GB | | [lambda-qwen2.5-14b-dpo-test.Q5_1.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q5_1.gguf) | Q5_1 | 10.38GB | | [lambda-qwen2.5-14b-dpo-test.Q6_K.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q6_K.gguf) | Q6_K | 11.29GB | | [lambda-qwen2.5-14b-dpo-test.Q8_0.gguf](https://huggingface.co/RichardErkhov/tanliboy_-_lambda-qwen2.5-14b-dpo-test-gguf/blob/main/lambda-qwen2.5-14b-dpo-test.Q8_0.gguf) | Q8_0 | 14.62GB | Original model description: --- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-14B-Instruct tags: - alignment-handbook - trl - dpo - generated_from_trainer - trl - dpo - generated_from_trainer datasets: - HuggingFaceH4/ultrafeedback_binarized model-index: - name: lambda-qwen2.5-14b-dpo-test results: [] --- # lambda-qwen2.5-14b-dpo-test This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set: - Loss: 0.4919 - Rewards/chosen: -2.4745 - Rewards/rejected: -3.3729 - Rewards/accuracies: 0.7400 - Rewards/margins: 0.8984 - Logps/rejected: -832.0724 - Logps/chosen: -737.5234 - Logits/rejected: -1.2739 - Logits/chosen: -1.2560 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 8 - total_train_batch_size: 128 - total_eval_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| | 0.5269 | 0.2094 | 100 | 0.5333 | -1.6756 | -2.3320 | 0.7000 | 0.6564 | -727.9815 | -657.6356 | -1.3952 | -1.3850 | | 0.5086 | 0.4187 | 200 | 0.5044 | -2.0906 | -2.9287 | 0.7040 | 0.8381 | -787.6511 | -699.1298 | -1.2939 | -1.2773 | | 0.4787 | 0.6281 | 300 | 0.4948 | -2.2927 | -3.1689 | 0.7320 | 0.8762 | -811.6696 | -719.3386 | -1.2846 | -1.2646 | | 0.4825 | 0.8375 | 400 | 0.4924 | -2.4470 | -3.3410 | 0.7400 | 0.8939 | -828.8748 | -734.7765 | -1.2644 | -1.2477 | ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1