Instructions to use ddwang2000/EchoChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ddwang2000/EchoChat with Transformers:

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

pipe = pipeline("text-generation", model="ddwang2000/EchoChat", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("ddwang2000/EchoChat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ddwang2000/EchoChat", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ddwang2000/EchoChat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ddwang2000/EchoChat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ddwang2000/EchoChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ddwang2000/EchoChat

SGLang

How to use ddwang2000/EchoChat 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 "ddwang2000/EchoChat" \
    --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": "ddwang2000/EchoChat",
		"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 "ddwang2000/EchoChat" \
        --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": "ddwang2000/EchoChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ddwang2000/EchoChat with Docker Model Runner:
```
docker model run hf.co/ddwang2000/EchoChat
```

EchoChat

File size: 1,343 Bytes

b6d2bc8

{
  "architectures": [
    "EchoChatForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_echochat.EchoChatConfig",
    "AutoModel": "modeling_echochat.EchoChatModel",
    "AutoModelForCausalLM": "modeling_echochat.EchoChatForCausalLM"
  },
  "bos_token_id": 151643,
  "eos_token_ids": [
    151644,
    151645
  ],
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "kimia_adaptor_input_dim": 5120,
  "kimia_audio_output_vocab": 16896,
  "kimia_media_begin": 151661,
  "kimia_media_end": 151663,
  "kimia_mimo_audiodelaytokens": 6,
  "kimia_mimo_layers": 6,
  "kimia_mimo_transformer_from_layer_index": 21,
  "kimia_text_output_vocab": 152064,
  "kimia_token_offset": 152064,
  "max_position_embeddings": 8192,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_audio_special_tokens": 512,
  "num_base_tokens": 151643,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pad_token_id": 152063,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_sliding_window": false,
  "use_whisper_feature": true,
  "vocab_size": 168448
}