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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/slim-extract-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-extract-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use llmware/slim-extract-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-extract-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-extract-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-extract-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-extract-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

doberst commited on Jun 21, 2024

Commit

46cb2e1

verified ·

1 Parent(s): 76c6d4f

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -1,19 +1,19 @@
 ---
-license: cc-by-sa-4.0
 inference: false
 ---
-# SLIM-EXTRACT
 <!-- Provide a quick summary of what the model is/does. -->
-**slim-extract** implements a specialized function-calling customizable 'extract' capability that takes as an input a context passage, a customized key, and outputs a python dictionary with key that corresponds to the customized key, with a value consisting of a list of items extracted from the text corresponding to that key, e.g.,
 &nbsp;&nbsp;&nbsp;&nbsp;`{'universities': ['Berkeley, Stanford, Yale, University of Florida, ...'] }`
-This model 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, we would recommend the 'quantized tool' version, e.g.,  [**'slim-extract-tool'**](https://huggingface.co/llmware/slim-extract-tool).
 ## Prompt format:
@@ -27,8 +27,8 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 <details>
 <summary>Transformers Script </summary>
-    model = AutoModelForCausalLM.from_pretrained("llmware/slim-extract")
-    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-extract")
     function = "extract"
     params = "company"
@@ -70,7 +70,7 @@ For fast inference use, we would recommend the 'quantized tool' version, e.g.,
 <summary>Using as Function Call in LLMWare</summary>
     from llmware.models import ModelCatalog
-    slim_model = ModelCatalog().load_model("llmware/slim-extract")
     response = slim_model.function_call(text,params=["company"], function="extract")
     print("llmware - llm_response: ", response)

 ---
+license: apache-2.0
 inference: false
 ---
+# SLIM-EXTRACT-TINY
 <!-- Provide a quick summary of what the model is/does. -->
+**slim-extract-tiny** implements a specialized function-calling customizable 'extract' capability that takes as an input a context passage, a customized key, and outputs a python dictionary with key that corresponds to the customized key, with a value consisting of a list of items extracted from the text corresponding to that key, e.g.,
 &nbsp;&nbsp;&nbsp;&nbsp;`{'universities': ['Berkeley, Stanford, Yale, University of Florida, ...'] }`
+This model is fine-tuned on top of a tiny-llama 1b base.
+For fast inference use, we would recommend the 'quantized tool' version, e.g.,  [**'slim-extract-tiny-tool'**](https://huggingface.co/llmware/slim-extract-tiny-tool).
 ## Prompt format:
 <details>
 <summary>Transformers Script </summary>
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-extract-tiny")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-extract-tiny")
     function = "extract"
     params = "company"
 <summary>Using as Function Call in LLMWare</summary>
     from llmware.models import ModelCatalog
+    slim_model = ModelCatalog().load_model("llmware/slim-extract-tiny")
     response = slim_model.function_call(text,params=["company"], function="extract")
     print("llmware - llm_response: ", response)