Instructions to use MultiverseComputingCAI/LittleLamb-ToolCalling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultiverseComputingCAI/LittleLamb-ToolCalling with Transformers:

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

pipe = pipeline("text-generation", model="MultiverseComputingCAI/LittleLamb-ToolCalling")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MultiverseComputingCAI/LittleLamb-ToolCalling")
model = AutoModelForCausalLM.from_pretrained("MultiverseComputingCAI/LittleLamb-ToolCalling")
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

vLLM

How to use MultiverseComputingCAI/LittleLamb-ToolCalling with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MultiverseComputingCAI/LittleLamb-ToolCalling

SGLang

How to use MultiverseComputingCAI/LittleLamb-ToolCalling 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 "MultiverseComputingCAI/LittleLamb-ToolCalling" \
    --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": "MultiverseComputingCAI/LittleLamb-ToolCalling",
		"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 "MultiverseComputingCAI/LittleLamb-ToolCalling" \
        --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": "MultiverseComputingCAI/LittleLamb-ToolCalling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MultiverseComputingCAI/LittleLamb-ToolCalling with Docker Model Runner:
```
docker model run hf.co/MultiverseComputingCAI/LittleLamb-ToolCalling
```

daniicruzz commited on 16 days ago

Commit

e7350ce

verified ·

1 Parent(s): 91ed35d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -251,12 +251,12 @@ BFCL V4 is the de facto industry standard for evaluating function-calling (tool-
 ### Quantitative Results (Inference Performance)
 #### Metrics reported
-- **System Output Throughput**: Mean output tokens per second across all concurrent requests over the benchmarking phase.
-- **End-to-End Latency per Query:** Median end-to-end response time for each query from the time the query is sent.
-- **Output Speed per Query:** Median output tokens per second after the first token is received for each query.
-- **Time to first token (TTFT):** Median
-- **Estimated Peak Memory Usage:** KV cache utilization is monitored during the phase and we estimate memory usage as follows: $model\_ weights_{gb} + kv\_ cache_{usage\_pct} × (nvml\_used_{gb} − model\_ weights_{gb})$
-- **Model weights:**
@@ -273,7 +273,7 @@ Our performance evaluation follows the spirit of [Artificial Analysis](https://a
 - **Streaming**: Benchmarking is conducted with streaming enabled.
-**Summary of improvements:** Little Lamb shows a slight improvement in performance with respect to the original Qwen Model. This is expected as for such small models, VRAM usage is dominated by KV cache and not model weights.
 ![Performance](assets/littlelamb-tc-performance-family.png)

 ### Quantitative Results (Inference Performance)
 #### Metrics reported
+- **System Output Throughput (higher is better)**: Mean output tokens per second across all concurrent requests over the benchmarking phase.
+- **End-to-End Latency per Query (lower is better):** Median end-to-end response time for each query from the time the query is sent.
+- **Output Speed per Query (higher is better):** Median output tokens per second after the first token is received for each query.
+- **Time to first token (TTFT) (lower is better):** Median
+- **Estimated Peak Memory Usage (lower is better):** KV cache utilization is monitored during the phase and we estimate memory usage as follows: $model\_ weights_{gb} + kv\_ cache_{usage\_pct} × (nvml\_used_{gb} − model\_ weights_{gb})$
+- **Model weights (lower is better):**
 - **Streaming**: Benchmarking is conducted with streaming enabled.
+**Summary of improvements:** LittleLamb shows a slight improvement in performance with respect to the original Qwen Model. This is expected as for such small models, VRAM usage is dominated by KV cache and not model weights.
 ![Performance](assets/littlelamb-tc-performance-family.png)