Feature Extraction
Transformers
Safetensors
English
multilingual
laya_browser
laya
custom_code
system-1
browser-agent
web-navigation
decision-model
mmbert
mind2web
tilelang
Instructions to use cklxx/laya-browser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cklxx/laya-browser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="cklxx/laya-browser", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cklxx/laya-browser", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download code/finetune/webgym/clean3.py from cklxx/laya-browser: direct link, hf CLI and curl.
- Browser
- Download file 1.16 kB
-
https://huggingface.co/cklxx/laya-browser/resolve/main/code/finetune/webgym/clean3.py
- Command line
-
hf download hf://cklxx/laya-browser/code/finetune/webgym/clean3.py
-
curl -L -o clean3.py https://huggingface.co/cklxx/laya-browser/resolve/main/code/finetune/webgym/clean3.py
1.16 kB
| """Keep only webgym episodes that reached a verified task_done (same filter as run_v17s.sh applies to gym_raw2): | |
| finetune/out/gym_raw3/g_<kind>_<seed0>.jsonl -> finetune/out/gym/clean3_<kind>_<seed0>.jsonl | |
| Prints per-file and per-kind episode / case counts.""" | |
| import json, glob, os, collections | |
| O = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "out") | |
| tot = collections.defaultdict(lambda: [0, 0, 0]) | |
| for f in sorted(glob.glob(f"{O}/gym_raw3/g_*.jsonl")): | |
| rows = [json.loads(l) for l in open(f)] | |
| good = {(r["gym_kind"], r["seed"]) for r in rows if r["skill"] == "task_done"} | |
| keep = [r for r in rows if (r["gym_kind"], r["seed"]) in good] | |
| out = f.replace("gym_raw3/g_", "gym/clean3_") | |
| open(out, "w").write("".join(json.dumps(r, ensure_ascii=False) + "\n" for r in keep)) | |
| kind = os.path.basename(f).split("_")[1] | |
| n_eps = len({r["seed"] for r in rows}) | |
| print(f"{os.path.basename(out):32s} episodes {len(good):4d}/{n_eps:<4d} cases {len(keep):6d}") | |
| t = tot[kind]; t[0] += len(good); t[1] += n_eps; t[2] += len(keep) | |
| for k, (g, n, c) in tot.items(): | |
| print(f"== {k:11s} clean episodes {g}/{n} cases {c}") | |