Introduction of ds7b-ep2-data10-ood-math-taskwise-lambda05
Model Details of ds7b-ep2-data10-ood-math-taskwise-lambda05
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 ds7b-ep2-data10-ood-math-taskwise-lambda05 on huggingface.co
7
Total runs
0
24-hour runs
0
3-day runs
2
7-day runs
7
30-day runs
More Information About ds7b-ep2-data10-ood-math-taskwise-lambda05 huggingface.co Model
ds7b-ep2-data10-ood-math-taskwise-lambda05 huggingface.co is an AI model on huggingface.co that provides ds7b-ep2-data10-ood-math-taskwise-lambda05's model effect (), which can be used instantly with this lejelly ds7b-ep2-data10-ood-math-taskwise-lambda05 model. huggingface.co supports a free trial of the ds7b-ep2-data10-ood-math-taskwise-lambda05 model, and also provides paid use of the ds7b-ep2-data10-ood-math-taskwise-lambda05. Support call ds7b-ep2-data10-ood-math-taskwise-lambda05 model through api, including Node.js, Python, http.
ds7b-ep2-data10-ood-math-taskwise-lambda05 huggingface.co is an online trial and call api platform, which integrates ds7b-ep2-data10-ood-math-taskwise-lambda05's modeling effects, including api services, and provides a free online trial of ds7b-ep2-data10-ood-math-taskwise-lambda05, you can try ds7b-ep2-data10-ood-math-taskwise-lambda05 online for free by clicking the link below.
lejelly ds7b-ep2-data10-ood-math-taskwise-lambda05 online free url in huggingface.co:
ds7b-ep2-data10-ood-math-taskwise-lambda05 is an open source model from GitHub that offers a free installation service, and any user can find ds7b-ep2-data10-ood-math-taskwise-lambda05 on GitHub to install. At the same time, huggingface.co provides the effect of ds7b-ep2-data10-ood-math-taskwise-lambda05 install, users can directly use ds7b-ep2-data10-ood-math-taskwise-lambda05 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
ds7b-ep2-data10-ood-math-taskwise-lambda05 install url in huggingface.co: