Instructions to use solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("solidrust/TinyLlama-1.1B-Chat-v1.0-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 solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/TinyLlama-1.1B-Chat-v1.0-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": "solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ

SGLang

How to use solidrust/TinyLlama-1.1B-Chat-v1.0-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 "solidrust/TinyLlama-1.1B-Chat-v1.0-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": "solidrust/TinyLlama-1.1B-Chat-v1.0-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 "solidrust/TinyLlama-1.1B-Chat-v1.0-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": "solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/TinyLlama-1.1B-Chat-v1.0-AWQ
```

TinyLlama-1.1B-Chat-v1.0-AWQ / README.md

Suparious

Update README.md

88bad18 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

1.79 kB

metadata

license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
datasets:
  - cerebras/SlimPajama-627B
  - bigcode/starcoderdata
  - HuggingFaceH4/ultrachat_200k
  - HuggingFaceH4/ultrafeedback_binarized
language:
  - en
widget:
  - example_title: Fibonacci (Python)
    messages:
      - role: system
        content: You are a chatbot who can help code!
      - role: user
        content: >-
          Write me a function to calculate the first 10 digits of the fibonacci
          sequence in Python and print it out to the CLI.
tags:
  - transformers
  - safetensors
  - finetuned
  - 4-bit
  - AWQ
  - text-generation
  - text-generation-inference
  - autotrain_compatible
  - endpoints_compatible
  - chatml
model_creator: TinyLlama
model_name: TinyLlama-1.1B-Chat-v1.0
inference: false
pipeline_tag: text-generation
quantized_by: Suparious

TinyLlama/TinyLlama-1.1B-Chat-v1.0 AWQ

Model creator: TinyLlama
Original model: TinyLlama-1.1B-Chat-v1.0

Model Summary

This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T. We follow HF's Zephyr's training recipe. The model was " initially fine-tuned on a variant of the UltraChat dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with 🤗 TRL's DPOTrainer on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4."