Instructions to use lfhe/FLock-Arena-Task-16-RoleWeaver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lfhe/FLock-Arena-Task-16-RoleWeaver with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "lfhe/FLock-Arena-Task-16-RoleWeaver")

Transformers

How to use lfhe/FLock-Arena-Task-16-RoleWeaver with Transformers:

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

pipe = pipeline("text-generation", model="lfhe/FLock-Arena-Task-16-RoleWeaver")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lfhe/FLock-Arena-Task-16-RoleWeaver", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lfhe/FLock-Arena-Task-16-RoleWeaver with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lfhe/FLock-Arena-Task-16-RoleWeaver"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lfhe/FLock-Arena-Task-16-RoleWeaver",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lfhe/FLock-Arena-Task-16-RoleWeaver

SGLang

How to use lfhe/FLock-Arena-Task-16-RoleWeaver 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 "lfhe/FLock-Arena-Task-16-RoleWeaver" \
    --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": "lfhe/FLock-Arena-Task-16-RoleWeaver",
		"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 "lfhe/FLock-Arena-Task-16-RoleWeaver" \
        --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": "lfhe/FLock-Arena-Task-16-RoleWeaver",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lfhe/FLock-Arena-Task-16-RoleWeaver with Docker Model Runner:
```
docker model run hf.co/lfhe/FLock-Arena-Task-16-RoleWeaver
```

lfhe commited on Oct 30, 2025

Commit

bfbc774

verified ·

1 Parent(s): c7ec8b2

update

Browse files

Files changed (2) hide show

adapter_config.json +5 -5
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -15,20 +15,20 @@
   "loftq_config": {},
   "lora_alpha": 96,
   "lora_bias": false,
-  "lora_dropout": 0.15,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_up_proj",
-    "qkv_proj",
-    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "loftq_config": {},
   "lora_alpha": 96,
   "lora_bias": false,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
+  "r": 96,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_up_proj",
+    "down_proj",
+    "qkv_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fd1554821aa07d80b9023d4dece3898234c89eba1cecae48defaadb8f9d803
-size 158092176

 version https://git-lfs.github.com/spec/v1
+oid sha256:a110dddc2fc53e0e9ed30dcb6f61500db4e03441f7282c7fb9a4c51fe08ced18
+size 237128664