Sponsored by Skywork
Toolify Toolify logo
AI Models
deepseek-ep3-data10-taskwise-lambda03

lejelly / deepseek-ep3-data10-taskwise-lambda03

Run on huggingface.co
huggingface.co
Total runs: 3
24-hour runs: 0
7-day runs: 1
30-day runs: 2
Model's Last Updated: October 09 2025

Introduction of deepseek-ep3-data10-taskwise-lambda03

Model Details of deepseek-ep3-data10-taskwise-lambda03

Merged Model using LLM-AdaMerge (task_wise)

This model was created by merging multiple fine-tuned models using the LLM-AdaMerge approach with task_wise merging.

Merge Details
  • Merge Type : task_wise
  • Base Model : deepseek-ai/deepseek-coder-7b-base-v1.5
  • Number of Models Merged : 2
  • Models Merged : math, code
  • Final Training Loss : N/A
  • Training Epochs : 0
Lambda Coefficients

The following lambda coefficients were learned during training:

Task-wise lambda coefficients are stored in the learned_lambdas.json file.

Usage 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("your-username/model-name")
tokenizer = AutoTokenizer.from_pretrained("your-username/model-name")

# Use the model
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))
Training Configuration

See the uploaded training_config.json file for detailed training configuration.

Citation

If you use this model, please cite the LLM-AdaMerge paper: 

@article{llmadamerge2024,
  title={LLM-AdaMerge: Adaptive Model Merging for Large Language Models},
  author={...},
  year={2024}
}

Runs of lejelly deepseek-ep3-data10-taskwise-lambda03 on huggingface.co

3
Total runs
0
24-hour runs
0
3-day runs
1
7-day runs
2
30-day runs

More Information About deepseek-ep3-data10-taskwise-lambda03 huggingface.co Model

deepseek-ep3-data10-taskwise-lambda03 huggingface.co

deepseek-ep3-data10-taskwise-lambda03 huggingface.co is an AI model on huggingface.co that provides deepseek-ep3-data10-taskwise-lambda03's model effect (), which can be used instantly with this lejelly deepseek-ep3-data10-taskwise-lambda03 model. huggingface.co supports a free trial of the deepseek-ep3-data10-taskwise-lambda03 model, and also provides paid use of the deepseek-ep3-data10-taskwise-lambda03. Support call deepseek-ep3-data10-taskwise-lambda03 model through api, including Node.js, Python, http.

deepseek-ep3-data10-taskwise-lambda03 huggingface.co Url

https://huggingface.co/lejelly/deepseek-ep3-data10-taskwise-lambda03

lejelly deepseek-ep3-data10-taskwise-lambda03 online free

deepseek-ep3-data10-taskwise-lambda03 huggingface.co is an online trial and call api platform, which integrates deepseek-ep3-data10-taskwise-lambda03's modeling effects, including api services, and provides a free online trial of deepseek-ep3-data10-taskwise-lambda03, you can try deepseek-ep3-data10-taskwise-lambda03 online for free by clicking the link below.

lejelly deepseek-ep3-data10-taskwise-lambda03 online free url in huggingface.co:

https://huggingface.co/lejelly/deepseek-ep3-data10-taskwise-lambda03

deepseek-ep3-data10-taskwise-lambda03 install

deepseek-ep3-data10-taskwise-lambda03 is an open source model from GitHub that offers a free installation service, and any user can find deepseek-ep3-data10-taskwise-lambda03 on GitHub to install. At the same time, huggingface.co provides the effect of deepseek-ep3-data10-taskwise-lambda03 install, users can directly use deepseek-ep3-data10-taskwise-lambda03 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

deepseek-ep3-data10-taskwise-lambda03 install url in huggingface.co:

https://huggingface.co/lejelly/deepseek-ep3-data10-taskwise-lambda03

Url of deepseek-ep3-data10-taskwise-lambda03

deepseek-ep3-data10-taskwise-lambda03 huggingface.co Url

Provider of deepseek-ep3-data10-taskwise-lambda03 huggingface.co

lejelly
ORGANIZATIONS
huggingface.co

Other API from lejelly