Instructions to use nicholasKluge/TeenyTinyLlama-460m-Chat-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nicholasKluge/TeenyTinyLlama-460m-Chat-awq with Transformers:

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

pipe = pipeline("text-generation", model="nicholasKluge/TeenyTinyLlama-460m-Chat-awq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/TeenyTinyLlama-460m-Chat-awq")
model = AutoModelForMultimodalLM.from_pretrained("nicholasKluge/TeenyTinyLlama-460m-Chat-awq")
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 Settings

vLLM

How to use nicholasKluge/TeenyTinyLlama-460m-Chat-awq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nicholasKluge/TeenyTinyLlama-460m-Chat-awq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nicholasKluge/TeenyTinyLlama-460m-Chat-awq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nicholasKluge/TeenyTinyLlama-460m-Chat-awq

SGLang

How to use nicholasKluge/TeenyTinyLlama-460m-Chat-awq 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 "nicholasKluge/TeenyTinyLlama-460m-Chat-awq" \
    --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": "nicholasKluge/TeenyTinyLlama-460m-Chat-awq",
		"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 "nicholasKluge/TeenyTinyLlama-460m-Chat-awq" \
        --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": "nicholasKluge/TeenyTinyLlama-460m-Chat-awq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nicholasKluge/TeenyTinyLlama-460m-Chat-awq with Docker Model Runner:
```
docker model run hf.co/nicholasKluge/TeenyTinyLlama-460m-Chat-awq
```

nicholasKluge commited on Jan 15, 2025

Commit

058938c

verified ·

1 Parent(s): 25e44e9

Update generation_config.json

Browse files

Files changed (1) hide show

generation_config.json +8 -10

generation_config.json CHANGED Viewed

@@ -1,16 +1,14 @@
 {
   "bos_token_id": 1,
-  "do_sample": true,
   "eos_token_id": 2,
-  "max_new_tokens": 2048,
   "pad_token_id": 3,
   "renormalize_logits": true,
   "repetition_penalty": 1.2,
-  "sep_token_id": null,
-  "temperature": 0.3,
-  "top_k": 30,
-  "top_p": 0.3,
-  "transformers_version": "4.35.2",
-  "unk_token_id": 0,
-  "use_cache": false
-}

 {
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 3,
+  "do_sample": true,
+  "max_new_tokens": 1024,
   "renormalize_logits": true,
   "repetition_penalty": 1.2,
+  "temperature": 0.1,
+  "top_k": 50,
+  "top_p": 1.0,
+  "use_cache": true,
+  "transformers_version": "4.42.3"
+}