Instructions to use Radu1999/ALLaM-7B-Toxic-Prompt-Detect with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Radu1999/ALLaM-7B-Toxic-Prompt-Detect with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("humain-ai/ALLaM-7B-Instruct-preview")
model = PeftModel.from_pretrained(base_model, "Radu1999/ALLaM-7B-Toxic-Prompt-Detect")

Transformers

How to use Radu1999/ALLaM-7B-Toxic-Prompt-Detect with Transformers:

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

pipe = pipeline("text-generation", model="Radu1999/ALLaM-7B-Toxic-Prompt-Detect")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Radu1999/ALLaM-7B-Toxic-Prompt-Detect")
model = AutoModelForCausalLM.from_pretrained("Radu1999/ALLaM-7B-Toxic-Prompt-Detect", 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 Radu1999/ALLaM-7B-Toxic-Prompt-Detect with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Radu1999/ALLaM-7B-Toxic-Prompt-Detect"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Radu1999/ALLaM-7B-Toxic-Prompt-Detect",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Radu1999/ALLaM-7B-Toxic-Prompt-Detect

SGLang

How to use Radu1999/ALLaM-7B-Toxic-Prompt-Detect 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 "Radu1999/ALLaM-7B-Toxic-Prompt-Detect" \
    --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": "Radu1999/ALLaM-7B-Toxic-Prompt-Detect",
		"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 "Radu1999/ALLaM-7B-Toxic-Prompt-Detect" \
        --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": "Radu1999/ALLaM-7B-Toxic-Prompt-Detect",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Radu1999/ALLaM-7B-Toxic-Prompt-Detect with Docker Model Runner:
```
docker model run hf.co/Radu1999/ALLaM-7B-Toxic-Prompt-Detect
```

Radu1999 commited on 13 days ago

Commit

5890cd1

verified ·

1 Parent(s): 721620c

Upload PEFT adapter

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
config.json +28 -0

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd144bc5d79598126ce9652373d8b603d0d4f046f531bf1fe13aaab13b2806a3
 size 80014016

 version https://git-lfs.github.com/spec/v1
+oid sha256:d916157bf14dcff64a7513ec49ca7fc4279f2f98ae52511fc31069903431b691
 size 80014016

config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.006,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 64000,
+  "internal_version": "7b-alpha-v2.33.0.30"
+}