Instructions to use codys12/dshybridempty with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codys12/dshybridempty with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codys12/dshybridempty")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("codys12/dshybridempty", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use codys12/dshybridempty with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codys12/dshybridempty" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codys12/dshybridempty", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/codys12/dshybridempty
- SGLang
How to use codys12/dshybridempty 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 "codys12/dshybridempty" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codys12/dshybridempty", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "codys12/dshybridempty" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codys12/dshybridempty", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use codys12/dshybridempty with Docker Model Runner:
docker model run hf.co/codys12/dshybridempty
File size: 1,149 Bytes
d46f387 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 | {
"architectures": [
"DSHybridForCausalLM"
],
"attention_dropout": 0.0,
"attention_logit_aux_loss_coef": 0.01,
"attn_layer_offset": 2000,
"attn_layer_period": 8,
"attn_mode": "fused_recurrent",
"bos_token_id": 1,
"conv_size": 4,
"eos_token_id": 2,
"expand_ratio": 1,
"expert_layer_offset": 1,
"expert_layer_period": 2,
"fuse_cross_entropy": true,
"hidden_act": "swish",
"hidden_ratio": 1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": null,
"max_position_embeddings": 8096,
"model_type": "ds_hybrid",
"num_attention_heads": 32,
"num_experts": 8,
"num_experts_per_tok": 2,
"num_heads": 1,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"num_prediction_heads": 1,
"output_attention_logits": false,
"output_router_logits": false,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"router_aux_loss_coef": 0.001,
"share_conv_kernel": true,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.43.2",
"use_cache": true,
"use_lower_bound": false,
"use_short_conv": false,
"vocab_size": 128256
}
|