Instructions to use RobertML/sn6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RobertML/sn6b with Transformers:

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

pipe = pipeline("text-generation", model="RobertML/sn6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RobertML/sn6b")
model = AutoModelForCausalLM.from_pretrained("RobertML/sn6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RobertML/sn6b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RobertML/sn6b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RobertML/sn6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RobertML/sn6b

SGLang

How to use RobertML/sn6b 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 "RobertML/sn6b" \
    --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": "RobertML/sn6b",
		"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 "RobertML/sn6b" \
        --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": "RobertML/sn6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RobertML/sn6b with Docker Model Runner:
```
docker model run hf.co/RobertML/sn6b
```

RobertML commited on Apr 26, 2024

Commit

67f5f83

verified ·

1 Parent(s): 390d694

Upload StableLmForCausalLM

Browse files

Files changed (3) hide show

config.json +29 -0
generation_config.json +7 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "neurons/model-best-0.9991267374247486",
+  "architectures": [
+    "StableLmForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 100289,
+  "eos_token_id": 100290,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "use_qkv_bias": true,
+  "vocab_size": 100352
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 100289,
+  "eos_token_id": 100290,
+  "transformers_version": "4.38.2",
+  "use_cache": false
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:834127ac6df37e5d7443df3884a9217fd3804798d9f7cdfe9a70e9adc16dab6b
+size 3289069520