Instructions to use abc88767/2c23 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abc88767/2c23 with Transformers:

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

pipe = pipeline("text-generation", model="abc88767/2c23")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abc88767/2c23")
model = AutoModelForCausalLM.from_pretrained("abc88767/2c23")
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 abc88767/2c23 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abc88767/2c23"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abc88767/2c23",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abc88767/2c23

SGLang

How to use abc88767/2c23 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 "abc88767/2c23" \
    --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": "abc88767/2c23",
		"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 "abc88767/2c23" \
        --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": "abc88767/2c23",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abc88767/2c23 with Docker Model Runner:
```
docker model run hf.co/abc88767/2c23
```

abc88767 commited on May 12, 2024

Commit

e040ad5

verified ·

1 Parent(s): e1bbd38

Upload StableLmForCausalLM

Browse files

Files changed (2) hide show

config.json +0 -2
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -18,14 +18,12 @@
   "num_hidden_layers": 24,
   "num_key_value_heads": 32,
   "partial_rotary_factor": 0.25,
-  "qk_layernorm": false,
   "rope_scaling": null,
   "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.1",
   "use_cache": true,
-  "use_parallel_residual": false,
   "use_qkv_bias": true,
   "vocab_size": 100352
 }

   "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": "4.39.1",
   "use_cache": true,
   "use_qkv_bias": true,
   "vocab_size": 100352
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f7cd9619ccca67c1fe97da616f467ddf8a6fe33b23087380877d61a7bfe168
 size 3289069520

 version https://git-lfs.github.com/spec/v1
+oid sha256:91b1ca929558bba1ee23ca54fb9180c4a55d6a5a3f4b4cfbaac0f80b91321f79
 size 3289069520