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

Libraries

How to use Nanthasit/sakthai-coder-browser with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-coder-browser")
model = AutoModelForCausalLM.from_pretrained("Nanthasit/sakthai-coder-browser", device_map="auto")
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 Settings

vLLM

How to use Nanthasit/sakthai-coder-browser with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nanthasit/sakthai-coder-browser

SGLang

How to use Nanthasit/sakthai-coder-browser 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 "Nanthasit/sakthai-coder-browser" \
    --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": "Nanthasit/sakthai-coder-browser",
		"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 "Nanthasit/sakthai-coder-browser" \
        --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": "Nanthasit/sakthai-coder-browser",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nanthasit/sakthai-coder-browser with Docker Model Runner:
```
docker model run hf.co/Nanthasit/sakthai-coder-browser
```

SakThai Coder Browser

Browser automation agent — Qwen2.5-Coder-1.5B-Instruct fine-tuned for web interaction
Part of the SakThai Model Family

⚠ BROKEN — DO NOT DEPLOY (as of 2026-07-31) — The merged weights in this repo are corrupted by a faulty LoRA merge: all 84 attention-projection bias tensors are non-zero while Qwen2 initializes these biases to ZERO (layer-0 k_proj.bias absmean 27.7 / max 354). Multi-trial inference probes produced only whitespace loops — 0 tool calls, 0 valid JSON at temp ≤ 0.7. Full evidence: .eval_results/benchmark-20260731_052122.yaml. The fault is in the weights, not the GGUF conversion or the prompt format. The GGUF variant was converted from these same corrupted weights and must be re-checked; the LoRA adapter needs a clean re-merge. Treat this repo as not deployable until re-merged and re-verified.

Model Description

SakThai Coder Browser transforms Qwen2.5-Coder-1.5B-Instruct into a browser automation assistant that outputs structured <tool_call> XML/JSON for web interaction. It can navigate pages, click elements, type text, and extract content — designed to work with browser automation frameworks.

Available actions via <tool_call> XML:

Tool	Example
`browser_navigate(url)`	`<tool_call>{"name": "browser_navigate", "arguments": {"url": "https://example.com"}}</tool_call>`
`browser_click(element)`	`<tool_call>{"name": "browser_click", "arguments": {"element": "#search-button"}}</tool_call>`
`browser_type(element, text)`	`<tool_call>{"name": "browser_type", "arguments": {"element": "#search-input", "text": "AI news"}}</tool_call>`
`browser_extract()`	`<tool_call>{"name": "browser_extract", "arguments": {}}</tool_call>`

Tool-Calling Format

The repo ships its own chat_template.jinja (Qwen2.5 tool-calling style). When tools are provided, the system prompt embeds function signatures inside <tools></tools> XML tags and the model replies with a <tool_call> JSON block:

<|im_start|>system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

# Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "browser_navigate", "parameters": {...}}}
</tools>

For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call><|im_end|>
<|im_start|>user
Search for the latest AI news.<|im_end|>
<|im_start|>assistant
<tool_call>
{"name": "browser_navigate", "arguments": {"url": "https://news.google.com"}}
</tool_call><|im_end|>

Tool results are wrapped in <tool_response></tool_response> blocks. Multi-turn loops are supported by the chat template.

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Nanthasit/sakthai-coder-browser",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-coder-browser")

messages = [
    {"role": "system", "content": "You are SakThai Browser Agent. Use <tool_call> blocks to control the browser."},
    {"role": "user", "content": "Search for the latest AI news and summarize the top story."},
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.3)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))

Expected output format:

<tool_call>{"name": "browser_navigate", "arguments": {"url": "https://news.google.com"}}</tool_call>

⚠️ Use the chat template. This model was trained with the Qwen2.5 tool-calling format — pass tools through apply_chat_template (or the repo's chat_template.jinja) rather than hand-rolling prompts.

GGUF / llama.cpp variant

Prefer CPU inference or Ollama? Use the GGUF build (F16, ~7.1 GB) with llama.cpp:

huggingface-cli download Nanthasit/sakthai-coder-browser-gguf \
  sakthai-coder-browser-f16.gguf --local-dir ./
./llama-cli -m sakthai-coder-browser-f16.gguf \
  -p "<|im_start|>system\nYou are a browser automation assistant.<|im_end|>\n<|im_start|>user\nGo to google.com and search for the latest AI news<|im_end|>\n<|im_start|>assistant\n" \
  -n 512 -t 8 --temp 0.3

Architecture

Verified from this repo's config.json (transformers 5.14.1):

Property	Value
Base Model	Qwen/Qwen2.5-Coder-1.5B-Instruct
Architecture	Qwen2ForCausalLM (decoder-only transformer)
Parameters	1,543,714,304 (1.54B)
Hidden Size	1,536
Layers	28
Attention Heads	12 (GQA, 2 KV heads)
Intermediate Size	8,960
Max Position	32,768 tokens
Vocab Size	151,936
RoPE θ	1,000,000
Activation	SiLU (SwiGLU)
Normalization	RMSNorm (eps=1e-6)
Precision	BF16
Weights	Single `model.safetensors` — 3,087,467,144 B (2.88 GB, API-verified)
Tied embeddings	yes (`tie_word_embeddings: true`)

Training Details

Detail	Value
Base model	Qwen/Qwen2.5-Coder-1.5B-Instruct
Method	SFT via LoRA (r=16, α=32, dropout 0.05, rsLoRA) on all 7 linear projections, then merged to full weights
Training data	SimpleToolCalling + sakthai-combined-v7
Context length	32,768 tokens
Precision	BF16
Hardware	Free T4 GPU (Kaggle / Colab)
Budget	$0

Training configuration mirrors the sibling sakthai-coder-browser-lora adapter (verified from its adapter_config.json: peft 0.20.0, use_rslora: true, lora_dropout: 0.05, target modules q/k/v/o/gate/up/down_proj).

Evaluation & Status

Honest status: inference benchmarks were attempted and did not produce output. The repo's own .eval_results/benchmark-20260731_052122.yaml records a llama.cpp GGUF Q4_K_M run (3 trials, CPU, 2 threads, 2026-07-31 05:21 UTC, tool-calling browser prompt, 244 input tokens) in which all 3 trials returned 0 output tokens — no tool call, no valid JSON, no correct answer:

Trial	Seed	Tool call	Valid JSON	Correct answer
1	7	❌	❌	❌
2	42	❌	❌	❌
3	1337	❌	❌	❌

Verdict — MODEL_BROKEN (bias corruption): the repo's own eval YAML (updated 2026-07-31 05:50 UTC) includes weight inspection of model.safetensors that proves the fault is in the weights, not the harness:

Qwen2 initializes attention-projection biases to zero; this merge left all 84 bias tensors non-zero (absmean > 0.01), e.g. layer-0 k_proj.bias absmean 27.7 / max 354, layer-0 q_proj.bias absmean 1.17
Degenerate generation at temp ≤ 0.7 on all 3 seeds — whitespace loops (150 newline tokens, 0 tool calls, 0 valid JSON); only at temp 1.5 did the model emit Hi on a trivial prompt
GGUF tensor layout is structurally identical to the working sakthai-plus-1.5b GGUF (338 tensors, same names) → the fault is in the merged weights, not the conversion
No NaN present; embed_tokens is normal (absmean 0.0136) — corruption is isolated to the attention biases

Recommended fix: re-merge the LoRA adapter into Qwen2.5-Coder-1.5B-Instruct with correct bias handling (do not write adapter-state biases into the base where Qwen2 expects zeros), re-run the multi-trial probe, and update this card. Until then, this repo is not deployable.

Hosted inference: not available — router probe returned 404 (Not Found) and the legacy api-inference host does not resolve (per the same eval YAML). No model-index is published because there are no verified scores yet; publishing one would be misleading.

Ecosystem status from .eval_results/cron-eval-sakthai-coder-browser-2026-07-30-1.yaml: card quality 85/100, repo hygiene 95/100, health 23/100 (rank 20/20 — new repo, zero downloads at eval time; popularity/momentum/benchmarks components are 0 because the repo had no traction yet).

Repo Contents

File	Size	Purpose
`model.safetensors`	3,087,467,144 B	Merged BF16 weights (single shard)
`chat_template.jinja`	2,507 B	Qwen2.5 tool-calling chat template
`config.json`	1,373 B	Qwen2 config (32K ctx, GQA 2 KV heads)
`tokenizer.json`	11,421,892 B	Tokenizer
`.eval_results/`	—	benchmark + cron-eval YAMLs

Sibling Models

Variant	Repository
LoRA Adapter (unmerged)	sakthai-coder-browser-lora
GGUF (llama.cpp / Ollama)	sakthai-coder-browser-gguf
Merged model (this repo) ⬅	sakthai-coder-browser

Model Family

One of 20 public models in the SakThai Model Family collection (21 including a private experimental embedding). Live download counts as of 2026-07-31; sizes API-verified from largest weight file.

Model	Size	Type	Downloads
Coder Browser (this model) ⬅	3.09 GB	Browser agent (merged)	0
Context 1.5B Merged	3.09 GB	Merged weights (flagship)	1,599
Context 0.5B Merged	988 MB	Merged weights (edge)	1,370
Context 7B Merged	15.2 GB	Merged weights (power)	744
Context 7B 128K	config-only	YaRN long-context recipe	506
Context 7B Tools	20.2 MB	LoRA adapter	399
Embedding Multilingual	471 MB	Embedding model	362
Context 1.5B Tools v1	~8.75 MB	LoRA adapter (v1)	349
Vision 7B	4.08 GB	Vision-language (GGUF)	186
TTS Model	141 MB	Kokoro-82M TTS (GGUF)	150
Context 0.5B Tools	988 MB	Merged weights	94
Coder 1.5B	1.12 GB	Code model (GGUF)	93
Context 1.5B Merged v2	3.09 GB	Merged weights	0
Context 1.5B Tools v2	73.9 MB	LoRA adapter	0
Coder Browser GGUF	7.11 GB	Browser agent F16 GGUF	0
Coder Browser LoRA	73.9 MB	LoRA adapter	0
Plus 1.5B	3.09 GB	Merged weights	0
Plus 1.5B LoRA	73.9 MB	LoRA adapter	0
Plus 1.5B Coder	—	Planned (no weights yet)	0

Limitations

Text-only — cannot see images or screenshots (use sakthai-vision-7b for vision tasks)
BROKEN weights — all 84 attention bias tensors are corrupted by a faulty LoRA merge (see Evaluation & Status); do not deploy until re-merged and re-verified
English only — trained primarily on English web data
Context-limited — best results with page content ≤ 4K tokens per interaction
Not servable on HF serverless inference — no provider supports this custom fine-tune (router 404 verified); run locally or via an Endpoint/GGUF