Downloads · 30 days
134
10% of all-time downloads
RichardErkhov/trl-lib_-_qwen1.5-0.5b-sft-gguf
trl-lib_-_qwen1.5-0.5b-sft-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
134
10% of all-time downloads
All-time downloads
1.3K
Public
Repo size
5.3 GB
Likes
0
Public
Click a slice to open those files.
.gguf6.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
qwen1.5-0.5b-sft - GGUF
| Name | Quant method | Size |
|---|---|---|
| qwen1.5-0.5b-sft.Q2_K.gguf | Q2_K | 0.23GB |
| qwen1.5-0.5b-sft.Q3_K_S.gguf | Q3_K_S | 0.25GB |
| qwen1.5-0.5b-sft.Q3_K.gguf | Q3_K | 0.26GB |
| qwen1.5-0.5b-sft.Q3_K_M.gguf | Q3_K_M | 0.26GB |
| qwen1.5-0.5b-sft.Q3_K_L.gguf | Q3_K_L | 0.28GB |
| qwen1.5-0.5b-sft.IQ4_XS.gguf | IQ4_XS | 0.28GB |
| qwen1.5-0.5b-sft.Q4_0.gguf | Q4_0 | 0.29GB |
| qwen1.5-0.5b-sft.IQ4_NL.gguf | IQ4_NL | 0.29GB |
| qwen1.5-0.5b-sft.Q4_K_S.gguf | Q4_K_S | 0.29GB |
| qwen1.5-0.5b-sft.Q4_K.gguf | Q4_K | 0.3GB |
| qwen1.5-0.5b-sft.Q4_K_M.gguf | Q4_K_M | 0.3GB |
| qwen1.5-0.5b-sft.Q4_1.gguf | Q4_1 | 0.3GB |
| qwen1.5-0.5b-sft.Q5_0.gguf | Q5_0 | 0.32GB |
| qwen1.5-0.5b-sft.Q5_K_S.gguf | Q5_K_S | 0.32GB |
| qwen1.5-0.5b-sft.Q5_K.gguf | Q5_K | 0.33GB |
| qwen1.5-0.5b-sft.Q5_K_M.gguf | Q5_K_M | 0.33GB |
| qwen1.5-0.5b-sft.Q5_1.gguf | Q5_1 | 0.34GB |
| qwen1.5-0.5b-sft.Q6_K.gguf | Q6_K | 0.36GB |
| qwen1.5-0.5b-sft.Q8_0.gguf | Q8_0 | 0.46GB |
license: other base_model: Qwen/Qwen1.5-0.5B tags:
This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the HuggingFaceH4/deita-6k-v0-sft dataset. 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 |
|---|---|---|---|
| 1.3015 | 1.0 | 237 | 1.2711 |
| 1.2352 | 2.0 | 474 | 1.2562 |
| 1.1719 | 3.0 | 711 | 1.2566 |