Instructions to use Blinorot/AL-SSLAM-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blinorot/AL-SSLAM-R with Transformers:

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

pipe = pipeline("text-generation", model="Blinorot/AL-SSLAM-R")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Blinorot/AL-SSLAM-R", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Blinorot/AL-SSLAM-R with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Blinorot/AL-SSLAM-R

SGLang

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

Docker Model Runner
How to use Blinorot/AL-SSLAM-R with Docker Model Runner:
```
docker model run hf.co/Blinorot/AL-SSLAM-R
```

AL-SSLAM-R / config.json

Blinorot

Upload Qwen3AudioWrappedForCausalLM

8468266 verified 3 months ago

raw

history blame contribute delete

2.34 kB

	{
	"architectures": [
	"Qwen3AudioWrappedForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"audio_adapter_configs": [
	{
	"adapter_embedding_dim": 1024,
	"adapter_name": "downsampler_conformer",
	"audio_encoder_layers": [
	3,
	7,
	11
	],
	"downsampler_depth": 1,
	"encoder_embedding_dim": 768,
	"encoder_name": "sslam",
	"layer_fusion_config": {
	"layer_fusion_type": "weighted_average"
	},
	"llm_embedding_dim": 2560,
	"norm_type": "layer",
	"pre_average": true,
	"use_conformer": false
	}
	],
	"audio_encoder_configs": [
	{
	"encoder_name": "sslam"
	}
	],
	"audio_fusion_config": {
	"fusion_type": "sum"
	},
	"audio_postprocessing_config": {
	"postprocessing_type": "identity"
	},
	"audio_sep_d_embed": 2560,
	"bos_token_id": 151643,
	"dtype": "float32",
	"eos_token_id": 151645,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 9728,
	"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",
	"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": 262144,
	"max_window_layers": 36,
	"model_type": "qwen3_audio",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 5000000,
	"sliding_window": null,
	"tie_word_embeddings": true,
	"transformers_version": "4.57.1",
	"use_cache": false,
	"use_explicit_audio_tokens": false,
	"use_sliding_window": false,
	"vocab_size": 151936
	}