Downloads · 30 days
27
1% of all-time downloads
RichardErkhov/tanliboy_-_llama-3.2-3b-dpo-gguf
tanliboy_-_llama-3.2-3b-dpo-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
27
1% of all-time downloads
All-time downloads
2K
Public
Repo size
38.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf44.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama-3.2-3b-dpo - GGUF
| Name | Quant method | Size |
|---|---|---|
| llama-3.2-3b-dpo.Q2_K.gguf | Q2_K | 1.27GB |
| llama-3.2-3b-dpo.IQ3_XS.gguf | IQ3_XS | 1.38GB |
| llama-3.2-3b-dpo.IQ3_S.gguf | IQ3_S | 1.44GB |
| llama-3.2-3b-dpo.Q3_K_S.gguf | Q3_K_S | 1.44GB |
| llama-3.2-3b-dpo.IQ3_M.gguf | IQ3_M | 1.49GB |
| llama-3.2-3b-dpo.Q3_K.gguf | Q3_K | 1.57GB |
| llama-3.2-3b-dpo.Q3_K_M.gguf | Q3_K_M | 1.57GB |
| llama-3.2-3b-dpo.Q3_K_L.gguf | Q3_K_L | 1.69GB |
| llama-3.2-3b-dpo.IQ4_XS.gguf | IQ4_XS | 1.71GB |
| llama-3.2-3b-dpo.Q4_0.gguf | Q4_0 | 1.79GB |
| llama-3.2-3b-dpo.IQ4_NL.gguf | IQ4_NL | 1.79GB |
| llama-3.2-3b-dpo.Q4_K_S.gguf | Q4_K_S | 1.8GB |
| llama-3.2-3b-dpo.Q4_K.gguf | Q4_K | 1.88GB |
| llama-3.2-3b-dpo.Q4_K_M.gguf | Q4_K_M | 1.88GB |
| llama-3.2-3b-dpo.Q4_1.gguf | Q4_1 | 1.95GB |
| llama-3.2-3b-dpo.Q5_0.gguf | Q5_0 | 2.11GB |
| llama-3.2-3b-dpo.Q5_K_S.gguf | Q5_K_S | 2.11GB |
| llama-3.2-3b-dpo.Q5_K.gguf | Q5_K | 2.16GB |
| llama-3.2-3b-dpo.Q5_K_M.gguf | Q5_K_M | 2.16GB |
| llama-3.2-3b-dpo.Q5_1.gguf | Q5_1 | 2.28GB |
| llama-3.2-3b-dpo.Q6_K.gguf | Q6_K | 2.46GB |
| llama-3.2-3b-dpo.Q8_0.gguf | Q8_0 | 3.19GB |
library_name: transformers license: llama3.2 base_model: tanliboy/llama-3.2-3b-sft tags:
This model is a fine-tuned version of tanliboy/llama-3.2-3b-sft on the HuggingFaceH4/orca_dpo_pairs and the HuggingFaceH4/ultrafeedback_binarized datasets. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5801 | 0.4739 | 100 | 0.6840 | 0.6485 | -2.9389 | 0.6899 | 3.5875 | -361.2435 | -339.3325 | 0.6783 | 0.6103 |
| 0.537 | 0.9479 | 200 | 0.6514 | 0.2045 | -4.0315 | 0.7278 | 4.2360 | -372.1696 | -343.7731 | 0.5648 | 0.4948 |
| 0.4787 | 1.4218 | 300 | 0.6387 | 0.4099 | -3.9882 | 0.7215 | 4.3981 | -371.7361 | -341.7187 | 0.5326 | 0.4589 |
| 0.4559 | 1.8957 | 400 | 0.6332 | 0.7690 | -3.6688 | 0.7342 | 4.4379 | -368.5425 | -338.1277 | 0.4841 | 0.4110 |
| 0.4028 | 2.3697 | 500 | 0.6289 | 0.7479 | -3.8379 | 0.7405 | 4.5857 | -370.2327 | -338.3392 | 0.4475 | 0.3731 |
| 0.4029 | 2.8436 | 600 | 0.6284 | 0.8504 | -3.7058 | 0.7437 | 4.5562 | -368.9125 | -337.3143 | 0.4571 | 0.3820 |