Downloads · 30 days
10
1% of all-time downloads
RichardErkhov/HyeongSoo_-_qwen-0.5b-sft-full-gguf
HyeongSoo_-_qwen-0.5b-sft-full-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
10
1% of all-time downloads
All-time downloads
1.9K
Public
Repo size
7.3 GB
Likes
0
Public
Click a slice to open those files.
.gguf8.5 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
qwen-0.5b-sft-full - GGUF
| Name | Quant method | Size |
|---|---|---|
| qwen-0.5b-sft-full.Q2_K.gguf | Q2_K | 0.32GB |
| qwen-0.5b-sft-full.IQ3_XS.gguf | IQ3_XS | 0.32GB |
| qwen-0.5b-sft-full.IQ3_S.gguf | IQ3_S | 0.32GB |
| qwen-0.5b-sft-full.Q3_K_S.gguf | Q3_K_S | 0.32GB |
| qwen-0.5b-sft-full.IQ3_M.gguf | IQ3_M | 0.32GB |
| qwen-0.5b-sft-full.Q3_K.gguf | Q3_K | 0.33GB |
| qwen-0.5b-sft-full.Q3_K_M.gguf | Q3_K_M | 0.33GB |
| qwen-0.5b-sft-full.Q3_K_L.gguf | Q3_K_L | 0.34GB |
| qwen-0.5b-sft-full.IQ4_XS.gguf | IQ4_XS | 0.33GB |
| qwen-0.5b-sft-full.Q4_0.gguf | Q4_0 | 0.33GB |
| qwen-0.5b-sft-full.IQ4_NL.gguf | IQ4_NL | 0.33GB |
| qwen-0.5b-sft-full.Q4_K_S.gguf | Q4_K_S | 0.36GB |
| qwen-0.5b-sft-full.Q4_K.gguf | Q4_K | 0.37GB |
| qwen-0.5b-sft-full.Q4_K_M.gguf | Q4_K_M | 0.37GB |
| qwen-0.5b-sft-full.Q4_1.gguf | Q4_1 | 0.35GB |
| qwen-0.5b-sft-full.Q5_0.gguf | Q5_0 | 0.37GB |
| qwen-0.5b-sft-full.Q5_K_S.gguf | Q5_K_S | 0.38GB |
| qwen-0.5b-sft-full.Q5_K.gguf | Q5_K | 0.39GB |
| qwen-0.5b-sft-full.Q5_K_M.gguf | Q5_K_M | 0.39GB |
| qwen-0.5b-sft-full.Q5_1.gguf | Q5_1 | 0.39GB |
| qwen-0.5b-sft-full.Q6_K.gguf | Q6_K | 0.47GB |
| qwen-0.5b-sft-full.Q8_0.gguf | Q8_0 | 0.49GB |
library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-0.5B-Instruct tags:
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the HuggingFaceH4/ultrachat_200k 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 |
|---|---|---|---|
| 1.2863 | 1.0 | 30584 | 1.4074 |