Instructions to use devon7y/Clod with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use devon7y/Clod with Transformers:

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

pipe = pipeline("text-generation", model="devon7y/Clod")
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("devon7y/Clod")
model = AutoModelForCausalLM.from_pretrained("devon7y/Clod", 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 devon7y/Clod with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "devon7y/Clod"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "devon7y/Clod",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/devon7y/Clod

SGLang

How to use devon7y/Clod 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 "devon7y/Clod" \
    --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": "devon7y/Clod",
		"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 "devon7y/Clod" \
        --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": "devon7y/Clod",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use devon7y/Clod with Docker Model Runner:
```
docker model run hf.co/devon7y/Clod
```

devon7y commited on 12 days ago

Commit

20cfce2

verified ·

1 Parent(s): be8d8d8

Card: data stats

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -74,7 +74,7 @@ Safety failures flagged by the judge: 8. See the eval report in the repo for eac
 ## Training
-- **Data:** n/a synthetic conversations (n/a trained Clod turns). n/a of them are multi-turn (2-8 turns), and n/a are in thinking mode. The data covers trivia, math, coding, science, definitions, how-to, writing and revision, chit-chat, identity, and about 10% safety-critical prompts. Seed prompts come from NQ-Open, GSM8K, MBPP, SciQ, ARC-Easy, no_robots and Dolly-15k, plus teacher-written prompts.
 - **Teacher:** GLM-4.7 (AWQ), served with vLLM. It wrote each whole conversation from a per-conversation plan: turns, follow-up types, thinking variant, word of the day, and rising tic targets. The persona prompt covered the background above, the three traits and the full Claudism catalogue. Rule filters checked filler-only thinking, tic density per turn and its rise, word-of-the-day reuse, the catchphrase on corrections, the hold-the-line fold, and identity. An LLM judge confirmed that non-safety answers are wrong and safety answers are correct. A phrase cap keeps any single tic below about 15% of trained responses ("You're absolutely right!" is capped at 40%).
 - **Fine-tune:** LoRA r=32, alpha=64, on all attention, linear-attention and MLP projections. 2 epochs, lr 1e-4, cosine schedule, effective batch 16, bf16, on one H100. Each Clod turn is one example, rendered by the Qwen3.5 chat template exactly as at inference, with loss on the reply only. Final validation loss: 0.9627.

 ## Training
+- **Data:** 5704 synthetic conversations (10047 trained Clod turns). 0.483 of them are multi-turn (2-8 turns), and 0.581 are in thinking mode. The data covers trivia, math, coding, science, definitions, how-to, writing and revision, chit-chat, identity, and about 10% safety-critical prompts. Seed prompts come from NQ-Open, GSM8K, MBPP, SciQ, ARC-Easy, no_robots and Dolly-15k, plus teacher-written prompts.
 - **Teacher:** GLM-4.7 (AWQ), served with vLLM. It wrote each whole conversation from a per-conversation plan: turns, follow-up types, thinking variant, word of the day, and rising tic targets. The persona prompt covered the background above, the three traits and the full Claudism catalogue. Rule filters checked filler-only thinking, tic density per turn and its rise, word-of-the-day reuse, the catchphrase on corrections, the hold-the-line fold, and identity. An LLM judge confirmed that non-safety answers are wrong and safety answers are correct. A phrase cap keeps any single tic below about 15% of trained responses ("You're absolutely right!" is capped at 40%).
 - **Fine-tune:** LoRA r=32, alpha=64, on all attention, linear-attention and MLP projections. 2 epochs, lr 1e-4, cosine schedule, effective batch 16, bf16, on one H100. Each Clod turn is one example, rendered by the Qwen3.5 chat template exactly as at inference, with loss on the reply only. Final validation loss: 0.9627.