Instructions to use tomg-group-umd/step-00010720-baseline_2_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tomg-group-umd/step-00010720-baseline_2_0 with Transformers:

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

pipe = pipeline("text-generation", model="tomg-group-umd/step-00010720-baseline_2_0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tomg-group-umd/step-00010720-baseline_2_0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tomg-group-umd/step-00010720-baseline_2_0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tomg-group-umd/step-00010720-baseline_2_0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tomg-group-umd/step-00010720-baseline_2_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tomg-group-umd/step-00010720-baseline_2_0

SGLang

How to use tomg-group-umd/step-00010720-baseline_2_0 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 "tomg-group-umd/step-00010720-baseline_2_0" \
    --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": "tomg-group-umd/step-00010720-baseline_2_0",
		"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 "tomg-group-umd/step-00010720-baseline_2_0" \
        --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": "tomg-group-umd/step-00010720-baseline_2_0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tomg-group-umd/step-00010720-baseline_2_0 with Docker Model Runner:
```
docker model run hf.co/tomg-group-umd/step-00010720-baseline_2_0
```

step-00010720-baseline_2_0 / model.safetensors.index.json

smcleish

Upload RavenForCausalLM

48cf0dc verified over 1 year ago

Raw

History Blame Contribute Delete

6.19 kB

	{
	"metadata": {
	"total_size": 15645600384
	},
	"weight_map": {
	"freqs_cis": "model-00001-of-00004.safetensors",
	"lm_head.weight": "model-00004-of-00004.safetensors",
	"transformer.adapter.weight": "model-00001-of-00004.safetensors",
	"transformer.coda.0.attn.Wqkv.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.attn.proj.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.attn.qk_bias": "model-00003-of-00004.safetensors",
	"transformer.coda.0.mlp.fc.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.mlp.proj.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.norm_1.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.norm_2.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.norm_3.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.0.norm_4.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.attn.Wqkv.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.attn.proj.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.attn.qk_bias": "model-00003-of-00004.safetensors",
	"transformer.coda.1.mlp.fc.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.mlp.proj.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.norm_1.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.norm_2.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.norm_3.weight": "model-00003-of-00004.safetensors",
	"transformer.coda.1.norm_4.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.0.attn.Wqkv.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.0.attn.proj.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.0.attn.qk_bias": "model-00001-of-00004.safetensors",
	"transformer.core_block.0.mlp.fc.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.0.mlp.proj.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.0.norm_1.weight": "model-00001-of-00004.safetensors",
	"transformer.core_block.0.norm_2.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.0.norm_3.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.0.norm_4.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.attn.Wqkv.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.attn.proj.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.attn.qk_bias": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.mlp.fc.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.mlp.proj.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.norm_1.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.norm_2.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.norm_3.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.1.norm_4.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.attn.Wqkv.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.attn.proj.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.attn.qk_bias": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.mlp.fc.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.mlp.proj.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.norm_1.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.norm_2.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.norm_3.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.2.norm_4.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.3.attn.Wqkv.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.3.attn.proj.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.3.attn.qk_bias": "model-00002-of-00004.safetensors",
	"transformer.core_block.3.mlp.fc.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.3.mlp.proj.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.3.norm_1.weight": "model-00002-of-00004.safetensors",
	"transformer.core_block.3.norm_2.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.3.norm_3.weight": "model-00003-of-00004.safetensors",
	"transformer.core_block.3.norm_4.weight": "model-00003-of-00004.safetensors",
	"transformer.ln_f.weight": "model-00003-of-00004.safetensors",
	"transformer.prelude.0.attn.Wqkv.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.attn.proj.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.attn.qk_bias": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.mlp.fc.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.mlp.proj.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.norm_1.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.norm_2.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.norm_3.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.0.norm_4.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.attn.Wqkv.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.attn.proj.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.attn.qk_bias": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.mlp.fc.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.mlp.proj.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.norm_1.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.norm_2.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.norm_3.weight": "model-00001-of-00004.safetensors",
	"transformer.prelude.1.norm_4.weight": "model-00001-of-00004.safetensors",
	"transformer.wte.weight": "model-00001-of-00004.safetensors"
	}
	}