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

Libraries

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

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

pipe = pipeline("text-generation", model="rostlabs/rost-1b-base", 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-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rostlabs/rost-1b-base"
# 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-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

stefaniancu commited on 4 days ago

Commit

ed91ec8

verified ·

1 Parent(s): 1ede21f

Upload meta_011136.json with huggingface_hub

Browse files

Files changed (1) hide show

meta_011136.json +73 -0

meta_011136.json ADDED Viewed

	@@ -0,0 +1,73 @@

+{
+  "step": 11136,
+  "val_bpb": null,
+  "model_config": {
+    "sequence_len": 4096,
+    "vocab_size": 32768,
+    "n_layer": 24,
+    "n_head": 12,
+    "n_kv_head": 12,
+    "n_embd": 1536,
+    "window_pattern": "SSSL",
+    "rope_base": 100000
+  },
+  "user_config": {
+    "run": "rost-d24-production",
+    "device_type": "",
+    "compile_mode": "default",
+    "serial_compile_warmup": true,
+    "eager_optimizer": true,
+    "fp8": true,
+    "fp8_recipe": "tensorwise",
+    "depth": 24,
+    "aspect_ratio": 64,
+    "head_dim": 128,
+    "max_seq_len": 4096,
+    "window_pattern": "SSSL",
+    "rope_base": 100000,
+    "init_from_dir": null,
+    "init_from_step": null,
+    "num_iterations": -1,
+    "target_flops": -1.0,
+    "target_param_data_ratio": 16.0,
+    "device_batch_size": 8,
+    "total_batch_size": -1,
+    "embedding_lr": 0.3,
+    "unembedding_lr": 0.008,
+    "weight_decay": 0.28,
+    "matrix_lr": 0.02,
+    "scalar_lr": 0.5,
+    "warmup_steps": 40,
+    "warmdown_ratio": 0.3,
+    "final_lr_frac": 0.05,
+    "resume_from_step": 7795,
+    "stop_after_step": -1,
+    "reset_dataloader_on_resume": true,
+    "eval_every": -1,
+    "keep_last_n": 3,
+    "knowledge_every": -1,
+    "eval_tokens": 41943040,
+    "eval_device_batch_size": 4,
+    "eval_oom_policy": "contain",
+    "core_metric_every": 2000,
+    "core_metric_max_per_task": 500,
+    "sample_every": 2000,
+    "save_every": 400,
+    "no_save": false,
+    "model_tag": null
+  },
+  "device_batch_size": 8,
+  "max_seq_len": 4096,
+  "total_batch_size": 1048576,
+  "mix_manifest_sha256": "8507758167618e2797f4047daad90681a9b5198716fffb162f01617f55e7ffee",
+  "dataloader_state_dict": {
+    "pq_idx": 61,
+    "rg_idx": 32,
+    "epoch": 1
+  },
+  "loop_state": {
+    "min_val_bpb": Infinity,
+    "smooth_train_loss": 2.0582391531039184,
+    "total_training_time": 12804.236830234528
+  }
+}