Instructions to use AlignmentLab-AI/teensyorca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlignmentLab-AI/teensyorca with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlignmentLab-AI/teensyorca")
model = AutoModelForCausalLM.from_pretrained("AlignmentLab-AI/teensyorca")
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 AlignmentLab-AI/teensyorca with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AlignmentLab-AI/teensyorca

SGLang

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

Docker Model Runner
How to use AlignmentLab-AI/teensyorca with Docker Model Runner:
```
docker model run hf.co/AlignmentLab-AI/teensyorca
```

Alignment-Lab-AI commited on Jan 7, 2024

Commit

b120c04

1 Parent(s): 39782eb

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -13

config.json CHANGED Viewed

@@ -11,24 +11,12 @@
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
-  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,

   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
+  "max_position_embeddings": 8096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,