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
```

Nanthasit commited on Aug 1

Commit

c0f7a65

verified ·

1 Parent(s): a8fa4e3

docs: add reproduce eval/train sections, keep honest broken-state disclosure

Browse files

Files changed (1) hide show

README.md +48 -1

README.md CHANGED Viewed

@@ -27,7 +27,6 @@ tags:
 base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
 datasets:
 - Nanthasit/sakthai-combined-v8
-- Nanthasit/sakthai-combined-v8
 - Nanthasit/sakthai-combined-v11
 - Nanthasit/sakthai-irrelevance-supplement
 - Nanthasit/cycle-bench
@@ -297,6 +296,54 @@ One of **25 public model repos** in the [SakThai Model Family collection](https:
 ---
 ## Limitations
 - **BROKEN weights** — all 84 attention bias tensors are corrupted by a faulty LoRA merge (see [Evaluation & Status](#evaluation--status)); do not deploy until re-merged and re-verified

 base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
 datasets:
 - Nanthasit/sakthai-combined-v8
 - Nanthasit/sakthai-combined-v11
 - Nanthasit/sakthai-irrelevance-supplement
 - Nanthasit/cycle-bench
 ---
+## Reproduce Evaluation
+If you want to verify the broken-state diagnosis locally, run the same llama.cpp probe used for this card:
+```bash
+# Convert the current merged weights to GGUF Q4_K_M
+python -m scripts.convert_hf_to_gguf --outfile sakthai-coder-browser-q4_k_m.gguf --quant-type Q4_K_M ./sakthai-coder-browser
+# 3-trial probe, 2 threads, CPU only
+for seed in 7 42 1337; do
+  ./llama-cli -m sakthai-coder-browser-q4_k_m.gguf \
+    -p "$(cat prompts/browser_tool_call.txt)" \
+    -n 256 --temp 0.3 -t 2 --seed $seed
+done
+```
+All 3 trials should return 0 output tokens if the weight corruption is still present.
+If they produce normal `<tool_call>` JSON blocks, the repo has been repaired.
+---
+## Reproduce Training / Merge
+The merged weights were produced by applying the LoRA adapter onto `Qwen/Qwen2.5-Coder-1.5B-Instruct`. To reproduce or repair:
+```bash
+git clone https://huggingface.co/Nanthasit/sakthai-coder-browser-lora adapter
+python -m peft.merge_and_unload \
+  --base_model Qwen/Qwen2.5-Coder-1.5B-Instruct \
+  --adapter adapter \
+  --output repaired-merged \
+  --safe
+```
+Important: zero-out attention-projection biases after merge if the base initializes them to zero:
+```python
+from transformers import AutoModelForCausalLM
+model = AutoModelForCausalLM.from_pretrained("repaired-merged", trust_remote_code=True)
+for name, param in model.named_parameters():
+    if "bias" in name and "attn" in name and "k_proj" in name:
+        param.data.zero_()
+```
+Run the eval probe again before publishing.
+---
 ## Limitations
 - **BROKEN weights** — all 84 attention bias tensors are corrupted by a faulty LoRA merge (see [Evaluation & Status](#evaluation--status)); do not deploy until re-merged and re-verified