Downloads · 30 days
7
6% of all-time downloads
HamadaMayu/qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1
qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1 is a text generation model from HamadaMayu. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This repository provides a merged full model fine-tuned for AgentBench tasks (ALFWorld + DBBench).
Downloads · 30 days
7
6% of all-time downloads
All-time downloads
125
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.2 GB · 100%
From the Hugging Face model README
This repository provides a merged full model fine-tuned for AgentBench tasks
(ALFWorld + DBBench).
Base model: Qwen/Qwen2.5-7B-Instruct
This repository contains fully merged model weights (LoRA merged into the base model).
This model is optimized for:
The model was trained using only officially provided training datasets:
Mixing strategy:
Base model: Qwen/Qwen2.5-7B-Instruct
Training framework:
Evaluation decoding configuration:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "HamadaMayu/qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1"
tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, device_map="auto", )
prompt = "Your task prompt here" inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate( **inputs, max_new_tokens=512, do_sample=False, temperature=0.0, )
print(tokenizer.decode(output[0], skip_special_tokens=True))