Instructions to use reaperdoesntknow/CasualSwarms with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reaperdoesntknow/CasualSwarms with Transformers:

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

pipe = pipeline("text-generation", model="reaperdoesntknow/CasualSwarms")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/CasualSwarms", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reaperdoesntknow/CasualSwarms with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/reaperdoesntknow/CasualSwarms

SGLang

How to use reaperdoesntknow/CasualSwarms 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 "reaperdoesntknow/CasualSwarms" \
    --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": "reaperdoesntknow/CasualSwarms",
		"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 "reaperdoesntknow/CasualSwarms" \
        --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": "reaperdoesntknow/CasualSwarms",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use reaperdoesntknow/CasualSwarms with Docker Model Runner:
```
docker model run hf.co/reaperdoesntknow/CasualSwarms
```

reaperdoesntknow commited on Jan 19

Commit

0ea8609

verified ·

1 Parent(s): a0f77ce

Upload swarm_tokenizer.json

Browse files

Files changed (1) hide show

swarm_tokenizer.json +32 -0

swarm_tokenizer.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "max_length": 2048,
+  "max_agents": 20,
+  "spec": {
+    "pad": "<|pad|>",
+    "bos": "<|bos|>",
+    "eos": "<|eos|>",
+    "unk": "<|unk|>",
+    "thought": "<|thought|>",
+    "action": "<|action|>",
+    "observe": "<|observe|>",
+    "route": "<|route|>",
+    "meta": "<|meta|>",
+    "system": "<|system|>",
+    "user": "<|user|>",
+    "assistant": "<|assistant|>",
+    "tool": "<|tool|>",
+    "agent_prefix": "<|agent:",
+    "agent_suffix": "|>",
+    "channel_id_map": {
+      "system": 0,
+      "user": 1,
+      "assistant": 2,
+      "thought": 3,
+      "action": 4,
+      "observe": 5,
+      "tool": 6,
+      "route": 7,
+      "meta": 8
+    }
+  }
+}