Downloads · 30 days
10
8% of all-time downloads
AlexChen1997/fedagent-webshop-grpo-hardness-std1-qwen2.5-1.5b
fedagent-webshop-grpo-hardness-std1-qwen2.5-1.5b is a text generation model from AlexChen1997. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
WebShop shopping-agent policy trained with federated GRPO on the FedAgent verl-0.8 stack. This repo holds the final aggregated global model (round 70) at the root, and the best-validation aggregate (round 68) under ch…
Downloads · 30 days
10
8% of all-time downloads
All-time downloads
126
Public
Parameters
1.5B
55.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors55.6 GB · 100%
From the Hugging Face model README
WebShop shopping-agent policy trained with federated GRPO on the FedAgent verl-0.8 stack.
This repo holds the final aggregated global model (round 70) at the root, and the
best-validation aggregate (round 68) under checkpoints/round_68/.
| Checkpoint | Val success rate (64 fixed episodes, temp 0.4) |
|---|---|
base Qwen/Qwen2.5-1.5B-Instruct | 4.7 % |
checkpoints/round_68/ (best) | 70.3 % |
| root = round 70 (final) | 64.1 % |
rollout.n=8, train_batch 8, prompt/response 4096/512, fused kernels (triton)base_seed 42 (fully deterministic schedule)search_return_n=50), 16-env pools per client, unperturbed shared val serviceconfig/paper_accelerated/task_heterogeneity/grpo/webshop/fed_webshop_grpo_total-100_cl-per-rd-2_rd-70_ep-per-cl-3_min-goals-per-cl-100_p-hardness_success_std-1.yaml (science knobs untouched)The full run record — per-round validation dumps, training logs, curves, and the official
federated_summary.json (71 global val points + 140 per-client circles) — is published
separately as a dataset: canyuchen/fedagent-webshop-grpo-hardness-std1.
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "canyuchen/fedagent-webshop-grpo-hardness-std1-qwen2.5-1.5b"
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained(repo)
# best-val checkpoint instead of the final one:
# model = AutoModelForCausalLM.from_pretrained(repo, subfolder="checkpoints/round_68", ...)
The agent expects WebShop-style observation/action prompting (as produced by the FedAgent rollout loop); it is not a general chat model, though the chat template is included.
Note on chat_template: verl's model_merger drops the tokenizer's chat_template when
exporting; it has been re-injected from the base Qwen tokenizer here, so
tok.apply_chat_template(...) works out of the box. If you re-export checkpoints from the raw
run artifacts yourself, remember to do the same.
model.safetensors.index.json included