Instructions to use RealDragonMA/Pelliculum-Chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RealDragonMA/Pelliculum-Chatbot with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RealDragonMA/Pelliculum-Chatbot")
model = AutoModelForCausalLM.from_pretrained("RealDragonMA/Pelliculum-Chatbot")
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 RealDragonMA/Pelliculum-Chatbot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RealDragonMA/Pelliculum-Chatbot

SGLang

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

Docker Model Runner
How to use RealDragonMA/Pelliculum-Chatbot with Docker Model Runner:
```
docker model run hf.co/RealDragonMA/Pelliculum-Chatbot
```

RealDragonMA commited on Feb 18, 2025

Commit

0c441a7

verified ·

1 Parent(s): 3126bf0

Model save

Browse files

Files changed (5) hide show

README.md +4 -4
final_checkpoint/adapter_config.json +2 -2
final_checkpoint/adapter_model.safetensors +1 -1
final_checkpoint/tokenizer.json +1 -6
final_checkpoint/training_args.bin +2 -2

README.md CHANGED Viewed

@@ -27,17 +27,17 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/realdragonma-pelliculum/huggingface/runs/gucz3wwp)
 This model was trained with SFT.
 ### Framework versions
-- TRL: 0.14.0
-- Transformers: 4.48.3
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.2.0
 - Tokenizers: 0.21.0
 ## Citations

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/realdragonma-pelliculum/huggingface/runs/wcdoae50)
 This model was trained with SFT.
 ### Framework versions
+- TRL: 0.15.0
+- Transformers: 4.49.0
 - Pytorch: 2.6.0+cu124
+- Datasets: 3.3.1
 - Tokenizers: 0.21.0
 ## Citations

final_checkpoint/adapter_config.json CHANGED Viewed

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
     "o_proj",
-    "v_proj",
-    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
     "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

final_checkpoint/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c0d86cfce92d8c1604bab7d4c9cc8c90cf852c6a21ec3bf0e5b294ed2ff9a2
 size 29523136

 version https://git-lfs.github.com/spec/v1
+oid sha256:bf7f8b223f35118ded6f308ce0488d12a93f556f0cc1e31b007ce46ae8940916
 size 29523136

final_checkpoint/tokenizer.json CHANGED Viewed

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

final_checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:468d6144abe817c443d42dc9f38248e1b7dacc79a09c721a19ae706c7c779e73
-size 5688

 version https://git-lfs.github.com/spec/v1
+oid sha256:19ffad974e6c86ba8d10a67fd65eeaea81497bd8351104df21e2567e618973a0
+size 5624