Instructions to use damerajee/Llamoe-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use damerajee/Llamoe-test with Transformers:

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

pipe = pipeline("text-generation", model="damerajee/Llamoe-test", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("damerajee/Llamoe-test", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use damerajee/Llamoe-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/damerajee/Llamoe-test

SGLang

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

Docker Model Runner
How to use damerajee/Llamoe-test with Docker Model Runner:
```
docker model run hf.co/damerajee/Llamoe-test
```

Llamoe-test / config.json

damerajee

Update config.json

f9a1080 verified over 2 years ago

Raw History Blame Contribute Delete

1.1 kB

{
  "_name_or_path": "damerajee/Llamoe-test",
  "architectures": [
    "LlamoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "damerajee/Llamoe-test--configuration_Llamoe.LlamoeConfig",
    "AutoModelForCausalLM": "damerajee/Llamoe-test--modeling_Llamoe.LlamoeForCausalLM",
    "AutoTokenizer": "damerajee/Llamoe-test--tokenizer_Llamoe.LlamoeTokenizer"

  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model_type": "Llamoe",
  "num_attention_heads": 32,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_local_experts": 4,
  "output_router_logits": false,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.38.2",
  "use_cache": true,
  "vocab_size": 32000
}

	{
	"_name_or_path": "damerajee/Llamoe-test",
	"architectures": [
	"LlamoeForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "damerajee/Llamoe-test--configuration_Llamoe.LlamoeConfig",
	"AutoModelForCausalLM": "damerajee/Llamoe-test--modeling_Llamoe.LlamoeForCausalLM",
	"AutoTokenizer": "damerajee/Llamoe-test--tokenizer_Llamoe.LlamoeTokenizer"

	},
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"max_position_embeddings": 4096,
	"model_type": "Llamoe",
	"num_attention_heads": 32,
	"num_experts_per_tok": 2,
	"num_hidden_layers": 32,
	"num_key_value_heads": 32,
	"num_local_experts": 4,
	"output_router_logits": false,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"router_aux_loss_coef": 0.001,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.38.2",
	"use_cache": true,
	"vocab_size": 32000
	}