Instructions to use llmware/slim-summary-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-summary-tiny with Transformers:

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

pipe = pipeline("text-generation", model="llmware/slim-summary-tiny")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/slim-summary-tiny")
model = AutoModelForCausalLM.from_pretrained("llmware/slim-summary-tiny")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llmware/slim-summary-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/slim-summary-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/slim-summary-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/llmware/slim-summary-tiny

SGLang

How to use llmware/slim-summary-tiny 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 "llmware/slim-summary-tiny" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/slim-summary-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "llmware/slim-summary-tiny" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/slim-summary-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use llmware/slim-summary-tiny with Docker Model Runner:
```
docker model run hf.co/llmware/slim-summary-tiny
```

doberst commited on Jun 21, 2024

Commit

1177311

verified ·

1 Parent(s): 3b46af1

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -1,13 +1,13 @@
 ---
-license: cc-by-sa-4.0
 inference: false
 ---
-# SLIM-SUMMARY
 <!-- Provide a quick summary of what the model is/does. -->
-**slim-summary** is a small, specialized model finetuned for summarize function-calls, generating output consisting of a python list of distinct summary points.
 As an experimental feature in the model, there is an optional list size that can be passed with the parameters in invoking the model to guide the model to a specific number of response elements.
@@ -15,9 +15,9 @@ Input is a text passage, and output is a list of the form:
 &nbsp;&nbsp;&nbsp;&nbsp;`['summary_point1', 'summary_point2', 'summary_point3']`
-This model is 2.7B parameters, small enough to run on a CPU, and is fine-tuned on top of [**llmware/bling-stable-lm-3b-4e1t-v0**](https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0), which in turn, is a fine-tune of stabilityai/stablelm-3b-4elt.
-For fast inference use of this model, we would recommend using the 'quantized tool' version, e.g.,  [**'slim-summary-tool'**](https://huggingface.co/llmware/slim-summary-tool).
 ## Usage Tips
@@ -41,8 +41,8 @@ For fast inference use of this model, we would recommend using the 'quantized to
 <details>
 <summary>Transformers Script </summary>
-    model = AutoModelForCausalLM.from_pretrained("llmware/slim-summary")
-    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-summary")
     function = "summarize"
     params = "key points (3)"
@@ -87,7 +87,7 @@ For fast inference use of this model, we would recommend using the 'quantized to
 <summary>Using as Function Call in LLMWare</summary>
     from llmware.models import ModelCatalog
-    slim_model = ModelCatalog().load_model("llmware/slim-summary")
     response = slim_model.function_call(text,params=["key points (3)], function="summarize")
     print("llmware - llm_response: ", response)

 ---
+license: apache-2.0
 inference: false
 ---
+# SLIM-SUMMARY-TINY
 <!-- Provide a quick summary of what the model is/does. -->
+**slim-summary-tiny** is a small, specialized model finetuned for summarize function-calls, generating output consisting of a python list of distinct summary points.
 As an experimental feature in the model, there is an optional list size that can be passed with the parameters in invoking the model to guide the model to a specific number of response elements.
 &nbsp;&nbsp;&nbsp;&nbsp;`['summary_point1', 'summary_point2', 'summary_point3']`
+This model is 1.1B parameters, small enough to run on a CPU, and is fine-tuned on top of a tiny-llama base.
+For fast inference use of this model, we would recommend using the 'quantized tool' version, e.g.,  [**'slim-summary-tiny-tool'**](https://huggingface.co/llmware/slim-summary-tiny-tool).
 ## Usage Tips
 <details>
 <summary>Transformers Script </summary>
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-summary-tiny")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-summary-tiny")
     function = "summarize"
     params = "key points (3)"
 <summary>Using as Function Call in LLMWare</summary>
     from llmware.models import ModelCatalog
+    slim_model = ModelCatalog().load_model("llmware/slim-summary-tiny")
     response = slim_model.function_call(text,params=["key points (3)], function="summarize")
     print("llmware - llm_response: ", response)