Instructions to use RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM with Transformers:

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

pipe = pipeline("text-generation", model="RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM")
model = AutoModelForCausalLM.from_pretrained("RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM", device_map="auto")
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 RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM

SGLang

How to use RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM 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 "RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM" \
    --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": "RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM",
		"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 "RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM" \
        --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": "RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM with Docker Model Runner:
```
docker model run hf.co/RakshitAralimatti/Qwen2.5-Coder-1.5B-Instruct-RASA-CALM
```

RakshitAralimatti commited on Dec 13, 2024

Commit

d908dd2

verified ·

1 Parent(s): b55c428

Update README.md

Browse files

Files changed (1) hide show

README.md +32 -1

README.md CHANGED Viewed

@@ -6,4 +6,35 @@ language:
 base_model:
 - Qwen/Qwen2.5-Coder-1.5B-Instruct
 library_name: transformers
----

 base_model:
 - Qwen/Qwen2.5-Coder-1.5B-Instruct
 library_name: transformers
+---
+# Qwen2.5-Coder-RASA-Calm
+This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on the RASA Calm dataset for improved command generation and intent understanding.
+### Model Description
+This model extends Qwen2.5-Coder's capabilities by specializing in natural language understanding and command generation for conversational AI applications, particularly in the context of the RASA framework.
+### Training Data
+The model was fine-tuned on the RASA Calm demonstration dataset (rasa/command-generation-calm-demo-v1), which contains examples of:
+Natural language user inputs
+Corresponding intents and entities
+Generated command structures
+## Model Architecture
+Base model: Qwen2.5-Coder-1.5B-Instruct
+Architecture: Transformer-based
+Parameters: 1.5B
+Context window: 8192 tokens
+## Intended Use
+This model is designed for:
+Converting natural language inputs into RASA-compatible commands
+Understanding user intents in conversational AI applications
+Generating structured outputs for chatbot development
+## Limitations
+The model's performance is optimized for the RASA framework and may not generalize well to other command generation tasks
+Limited to the scope of intents and entities present in the CALM dataset
+Inherits any limitations present in the base Qwen2.5-Coder model