Instructions to use patrickcmd/spark-tts-salt-lug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patrickcmd/spark-tts-salt-lug with Transformers:

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

pipe = pipeline("text-generation", model="patrickcmd/spark-tts-salt-lug")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("patrickcmd/spark-tts-salt-lug")
model = AutoModelForCausalLM.from_pretrained("patrickcmd/spark-tts-salt-lug", 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 patrickcmd/spark-tts-salt-lug with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/patrickcmd/spark-tts-salt-lug

SGLang

How to use patrickcmd/spark-tts-salt-lug 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 "patrickcmd/spark-tts-salt-lug" \
    --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": "patrickcmd/spark-tts-salt-lug",
		"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 "patrickcmd/spark-tts-salt-lug" \
        --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": "patrickcmd/spark-tts-salt-lug",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use patrickcmd/spark-tts-salt-lug with Docker Model Runner:
```
docker model run hf.co/patrickcmd/spark-tts-salt-lug
```

patrickcmd commited on Mar 18

Commit

4c22824

verified ·

1 Parent(s): affa27b

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show

README.md +1 -0
config.json +55 -0
generation_config.json +9 -0
model.safetensors +3 -0

README.md CHANGED Viewed

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - qwen2
 - trl
 license: apache-2.0
 language:
 - en

 - unsloth
 - qwen2
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "unsloth_version": "2026.2.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 166000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151645
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bebafae1df42b2b114c09755da6d89d39d052d3ba78b128b8923f21a847656f1
+size 2026568872