---
title: deepseek-coder-1.3B-kexer-GGUF
canonical_url: "https://www.modelscope.cn/models/QuantFactory/deepseek-coder-1.3B-kexer-GGUF"
md_url: "https://www.modelscope.cn/models/QuantFactory/deepseek-coder-1.3B-kexer-GGUF.md"
repository: QuantFactory/deepseek-coder-1.3B-kexer-GGUF
last_updated: 2025-06-22
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - transformer
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 2644
stars: 1
tags:
  - gguf
---

# deepseek-coder-1.3B-kexer-GGUF

> deepseek-coder-1.3B-kexer-GGUF - QuantFactory 在 ModelScope 开源的模型。QuantFactory/deepseek-coder-1.3B-kexer-GGUF This is quantized version of JetBrains/deepseek-coder-1.3B-kexer created using llama.cpp

- **Repository**: QuantFactory/deepseek-coder-1.3B-kexer-GGUF
- **Tasks**: text-generation
- **Tags**: gguf
- **Downloads**: 2644
- **Stars**: 1
- **Last updated**: 2025-06-22

Source: https://www.modelscope.cn/models/QuantFactory/deepseek-coder-1.3B-kexer-GGUF

---

[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)


# QuantFactory/deepseek-coder-1.3B-kexer-GGUF
This is quantized version of [JetBrains/deepseek-coder-1.3B-kexer](https://huggingface.co/JetBrains/deepseek-coder-1.3B-kexer) created using llama.cpp

# Original Model Card


# Kexer models

Kexer models are a collection of open-source generative text models fine-tuned on the [Kotlin Exercices](https://huggingface.co/datasets/JetBrains/KExercises) dataset. 
This is a repository for the fine-tuned **Deepseek-coder-1.3b** model in the *Hugging Face Transformers* format. 

# How to use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load pre-trained model and tokenizer
model_name = 'JetBrains/deepseek-coder-1.3B-kexer'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to('cuda')

# Create and encode input
input_text = """\
This function takes an integer n and returns factorial of a number:
fun factorial(n: Int): Int {\
"""
input_ids = tokenizer.encode(
    input_text, return_tensors='pt'
).to('cuda')

# Generate
output = model.generate(
    input_ids, max_length=60, num_return_sequences=1, 
    early_stopping=True, pad_token_id=tokenizer.eos_token_id,
)

# Decode output
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_text)
```

As with the base model, we can use FIM. To do this, the following format must be used: 
```
'<｜fim▁begin｜>' + prefix + '<｜fim▁hole｜>' + suffix + '<｜fim▁end｜>'
```

# Training setup

The model was trained on one A100 GPU with following hyperparameters:

|         **Hyperparameter**           |             **Value**              |
|:---------------------------:|:----------------------------------------:|
|           `warmup`            |           10%            |
|        `max_lr`        |          1e-4          |
|        `scheduler`        |          linear          |
|        `total_batch_size`        |          256 (~130K tokens per step)          |
|        `num_epochs`        |          4          |

More details about fine-tuning can be found in the technical report (coming soon!).

# Fine-tuning data

For tuning this model, we used 15K exmaples from the synthetically generated [Kotlin Exercices](https://huggingface.co/datasets/JetBrains/KExercises) dataset. Every example follows the HumanEval format. In total, the dataset contains about 3.5M tokens. 

# Evaluation 

For evaluation, we used the [Kotlin HumanEval](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval) dataset, which contains all 161 tasks from HumanEval translated into Kotlin by human experts. You can find more details about the pre-processing necessary to obtain our results, including the code for running, on the [datasets's page](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval).

Here are the results of our evaluation:

|         **Model name**           |             **Kotlin HumanEval Pass Rate**              |
|:---------------------------:|:----------------------------------------:|
|           `Deepseek-coder-1.3B`            |           26.71            |
|        `Deepseek-coder-1.3B-Kexer`        |          **36.65**         |

# Ethical considerations and limitations

Deepseek-coder-1.3B-Kexer is a new technology that carries risks with use. The testing conducted to date has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Deepseek-coder-1.3B-Kexer's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of Deepseek-coder-1.3B-Kexer, developers should perform safety testing and tuning tailored to their specific applications of the model.