Instructions to use rostlabs/rost-1b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rostlabs/rost-1b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="rostlabs/rost-1b-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("rostlabs/rost-1b-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rostlabs/rost-1b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rostlabs/rost-1b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rostlabs/rost-1b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rostlabs/rost-1b-instruct

SGLang

How to use rostlabs/rost-1b-instruct 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 "rostlabs/rost-1b-instruct" \
    --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": "rostlabs/rost-1b-instruct",
		"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 "rostlabs/rost-1b-instruct" \
        --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": "rostlabs/rost-1b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rostlabs/rost-1b-instruct with Docker Model Runner:
```
docker model run hf.co/rostlabs/rost-1b-instruct
```

stefaniancu commited on 7 days ago

Commit

4cb8a6e

verified ·

1 Parent(s): deca6d1

Upload meta_000387.json with huggingface_hub

Browse files

Files changed (1) hide show

meta_000387.json +57 -0

meta_000387.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+  "step": 387,
+  "val_bpb": 0.3020884011575493,
+  "model_config": {
+    "sequence_len": 4096,
+    "vocab_size": 32768,
+    "n_layer": 24,
+    "n_head": 12,
+    "n_kv_head": 12,
+    "n_embd": 1536,
+    "window_pattern": "SSSL"
+  },
+  "user_config": {
+    "run": "rost-d24-production",
+    "mixture": "romanian",
+    "identity_name": "rost",
+    "device_type": "",
+    "compile_mode": "default",
+    "serial_compile_warmup": true,
+    "eager_optimizer": true,
+    "init_source": "base",
+    "model_tag": null,
+    "model_step": null,
+    "output_model_tag": null,
+    "load_optimizer": 1,
+    "num_iterations": -1,
+    "max_seq_len": null,
+    "device_batch_size": 8,
+    "total_batch_size": null,
+    "embedding_lr": null,
+    "unembedding_lr": null,
+    "matrix_lr": null,
+    "init_lr_frac": 0.8,
+    "warmup_ratio": 0.0,
+    "warmdown_ratio": 0.5,
+    "final_lr_frac": 0.0,
+    "grad_clip": 0.0,
+    "eval_every": 200,
+    "eval_tokens": 20971520,
+    "save_every": 100,
+    "eval_device_batch_size": 4,
+    "chatcore_batch_size": -1,
+    "eval_oom_policy": "contain",
+    "chatcore_every": 200,
+    "chatcore_max_cat": -1,
+    "chatcore_max_sample": 24,
+    "dialogue_frac": 0.0,
+    "english_frac": 0.25,
+    "ro_gsm8k_epochs": 0,
+    "agent_traces": null,
+    "agent_epochs": 1,
+    "agent_frac": 0.0,
+    "agent_max_repeats": 1000,
+    "mmlu_epochs": 3,
+    "gsm8k_epochs": 4
+  }
+}