Instructions to use modrill/code-think-q8b-20260908 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/code-think-q8b-20260908 with Transformers:

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

pipe = pipeline("text-generation", model="modrill/code-think-q8b-20260908")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("modrill/code-think-q8b-20260908")
model = AutoModelForCausalLM.from_pretrained("modrill/code-think-q8b-20260908", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modrill/code-think-q8b-20260908 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/code-think-q8b-20260908"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/code-think-q8b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/code-think-q8b-20260908

SGLang

How to use modrill/code-think-q8b-20260908 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 "modrill/code-think-q8b-20260908" \
    --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": "modrill/code-think-q8b-20260908",
		"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 "modrill/code-think-q8b-20260908" \
        --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": "modrill/code-think-q8b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/code-think-q8b-20260908 with Docker Model Runner:
```
docker model run hf.co/modrill/code-think-q8b-20260908
```

modrill commited on Sep 10

Commit

1e9965b

verified ·

1 Parent(s): b53dd36

Rename card to code-think-q8b-20260909; formerly CodeThink-V4-Qwen3-8B

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ pipeline_tag: text-generation
 library_name: transformers
 ---
-# CodeThink-V4-Qwen3-8B
 Research checkpoint: **Qwen/Qwen3-8B-Base** (`49e3418fbbbca6ecbdf9608b4d22e5a407081db4`) after V4 LoRA SFT on Qwen3-30B-A3B-Thinking-2507 traces, then merged to full weights.
@@ -47,7 +47,7 @@ Merged weights are the 2-epoch endpoint (`step-000921`, 64,873,788 assistant tok
 | Model | pass@1 | Cap | Notes |
 |---|---:|---:|---|
-| **CodeThink-V4-Qwen3-8B** | **81/256** | **130** | this repo; seed 3407; V4 think contract |
 | Qwen3-8B-Base | 55/256 | — | **old-contract** historical bare-base number (not a same-contract V4 think-mode re-eval; a same-contract 8B-base think COMPLETE.json was not on disk) |
 Single seed. These are research checkpoints, not product scores.
@@ -61,7 +61,7 @@ Merged full weights; no PEFT required at inference. Think mode: `enable_thinking
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-repo = "modrill/CodeThink-V4-Qwen3-8B"
 tokenizer = AutoTokenizer.from_pretrained(repo)
 model = AutoModelForCausalLM.from_pretrained(
     repo, torch_dtype="bfloat16", device_map="auto"

 library_name: transformers
 ---
+# code-think-q8b-20260909
 Research checkpoint: **Qwen/Qwen3-8B-Base** (`49e3418fbbbca6ecbdf9608b4d22e5a407081db4`) after V4 LoRA SFT on Qwen3-30B-A3B-Thinking-2507 traces, then merged to full weights.
 | Model | pass@1 | Cap | Notes |
 |---|---:|---:|---|
+| **code-think-q8b-20260909** | **81/256** | **130** | this repo; seed 3407; V4 think contract |
 | Qwen3-8B-Base | 55/256 | — | **old-contract** historical bare-base number (not a same-contract V4 think-mode re-eval; a same-contract 8B-base think COMPLETE.json was not on disk) |
 Single seed. These are research checkpoints, not product scores.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+repo = "modrill/code-think-q8b-20260909"
 tokenizer = AutoTokenizer.from_pretrained(repo)
 model = AutoModelForCausalLM.from_pretrained(
     repo, torch_dtype="bfloat16", device_map="auto"