Instructions to use osanseviero/browser-actions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use osanseviero/browser-actions with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="osanseviero/browser-actions")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("osanseviero/browser-actions")
model = AutoModelForCausalLM.from_pretrained("osanseviero/browser-actions")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use osanseviero/browser-actions with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "osanseviero/browser-actions"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osanseviero/browser-actions",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/osanseviero/browser-actions

SGLang

How to use osanseviero/browser-actions with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "osanseviero/browser-actions" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osanseviero/browser-actions",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "osanseviero/browser-actions" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "osanseviero/browser-actions",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use osanseviero/browser-actions with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for osanseviero/browser-actions to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for osanseviero/browser-actions to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for osanseviero/browser-actions to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="osanseviero/browser-actions",
    max_seq_length=2048,
)

Docker Model Runner
How to use osanseviero/browser-actions with Docker Model Runner:
```
docker model run hf.co/osanseviero/browser-actions
```

Upload optimized ONNX model

by Xenova HF Staff - opened Jan 11

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+41

-51350

Files changed (7) hide show

config.json +26 -7
onnx/model.onnx_data +1 -1
onnx/model_fp16.onnx_data +1 -1
onnx/model_q4.onnx_data +1 -1
onnx/model_q4f16.onnx_data +1 -1
tokenizer.json +2 -2
tokenizer_config.json +0 -0

config.json CHANGED Viewed

@@ -7,7 +7,7 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
-  "torch_dtype": "float16",
   "eos_token_id": 106,
   "final_logit_softcapping": null,
   "head_dim": 256,
@@ -43,14 +43,33 @@
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000.0,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
   "sliding_window": 512,
-  "transformers_version": "4.57.3",
   "unsloth_fixed": true,
   "unsloth_version": "2026.1.2",
   "use_bidirectional_attention": false,
   "use_cache": true,
-  "vocab_size": 262144
-}

   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
+  "dtype": "float16",
   "eos_token_id": 106,
   "final_logit_softcapping": null,
   "head_dim": 256,
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
   "sliding_window": 512,
+  "transformers_version": "5.0.0.dev0",
   "unsloth_fixed": true,
   "unsloth_version": "2026.1.2",
   "use_bidirectional_attention": false,
   "use_cache": true,
+  "vocab_size": 262144,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": 1,
+      "model_fp16.onnx": 1,
+      "model_q4.onnx": 1,
+      "model_q4f16.onnx": 1
+    },
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    }
+  }
+}

onnx/model.onnx_data CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a55aebb86cfa1387698a09c5b1a75ae7ed75aa11e45f786ece3239641d1ac4
 size 1139501568

 version https://git-lfs.github.com/spec/v1
+oid sha256:b7d3a412f0da96eaa98edee828ce6c0dfebbbb9974485615ad14bab736526e08
 size 1139501568

onnx/model_fp16.onnx_data CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e9c33ae1b6dd9faaadb272c0adfbd60fd945552a4e790f5a04f0f632952354
 size 569862656

 version https://git-lfs.github.com/spec/v1
+oid sha256:e20f41ae1f64b827396fe58365d542d20f6d7f36e370701426446dfb59c153ee
 size 569862656

onnx/model_q4.onnx_data CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df04662e4eec6cceca86d2655c63d8d39a0faef245f9f43252f1c9a7ebbac878
 size 801090048

 version https://git-lfs.github.com/spec/v1
+oid sha256:abddf978d152ad7d57bc5f1a98504bdbd76ed72db808542b8149c369bb092faa
 size 801090048

onnx/model_q4f16.onnx_data CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f09ff1b5edb7fa34dc9dd3056fe24caa97a01ad9e38301fc826cc0778fc50ec
 size 425724416

 version https://git-lfs.github.com/spec/v1
+oid sha256:6fb1a1c91d28dac4c426e17df4b98127f04462a5e6ba23d639eb06a8c1bc3b6c
 size 425724416

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
-size 33384899

 version https://git-lfs.github.com/spec/v1
+oid sha256:1fa00479b9f9d41a876e5cd1b369eea7af974fa0bdcc994c987972056d8ed5c2
+size 20323384

tokenizer_config.json CHANGED Viewed

The diff for this file is too large to render. See raw diff