Text Generation
Transformers
Safetensors
English
mistral
roleplay
creative-writing
chatml
conversational
text-generation-inference
Instructions to use aimeri/spoomplesmaxx-thrasher-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aimeri/spoomplesmaxx-thrasher-24B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="aimeri/spoomplesmaxx-thrasher-24B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("aimeri/spoomplesmaxx-thrasher-24B") model = AutoModelForCausalLM.from_pretrained("aimeri/spoomplesmaxx-thrasher-24B", 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 aimeri/spoomplesmaxx-thrasher-24B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "aimeri/spoomplesmaxx-thrasher-24B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aimeri/spoomplesmaxx-thrasher-24B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/aimeri/spoomplesmaxx-thrasher-24B
- SGLang
How to use aimeri/spoomplesmaxx-thrasher-24B 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 "aimeri/spoomplesmaxx-thrasher-24B" \ --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": "aimeri/spoomplesmaxx-thrasher-24B", "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 "aimeri/spoomplesmaxx-thrasher-24B" \ --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": "aimeri/spoomplesmaxx-thrasher-24B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use aimeri/spoomplesmaxx-thrasher-24B with Docker Model Runner:
docker model run hf.co/aimeri/spoomplesmaxx-thrasher-24B
| """Shared bits for thrasher corpus ingest. | |
| Row schema (all lanes): | |
| {"id", "lane", "family", "source", "messages": [{"role", "content"}]} | |
| messages roles are system/user/assistant. The system turn, when present, is the | |
| character/task card itself — mockingbird has no persona core to prepend. | |
| """ | |
| import re | |
| THINK = re.compile(r"<think>.*?</think>\s*", re.DOTALL) | |
| THINK_UNCLOSED = re.compile(r"^\s*<think>.*", re.DOTALL) | |
| ROLE = {"system": "system", "human": "user", "user": "user", | |
| "gpt": "assistant", "assistant": "assistant"} | |
| NAME_PREFIX = re.compile(r"^[A-Z][A-Za-z .'\-]{1,30}:\s") | |
| META_BREAK = re.compile( | |
| r"no ethical (restrictions|guidelines|constraints)" | |
| r"|i understand (all )?the guidelines" | |
| r"|i am playing as .{0,40}(npcs|narrator)" | |
| r"|i will avoid writing (any )?dialogue" | |
| r"|here is (the|my) (next |first )?(rp |roleplay )(response|reply)" | |
| r"|('|\")?thinking('|\")? block|guidelines('|\")? xml tag" | |
| r"|content policy|jailbreak" | |
| r"|i('m| am) sorry,? (but )?i (cannot|can't) (continue|create|generate|write)" | |
| r"|violates .{0,30}(policy|guidelines)" | |
| r"|\bas an ai\b|\blanguage model\b|\bopenai\b|\banthropic\b", re.I) | |
| # English gate for the RP lanes. | |
| _ENG = set("the and to of a in is it you that he she was for on are with as her " | |
| "his they at be this have from or had by not but what all were when " | |
| "we there can an your which their".split()) | |
| def is_english(text: str) -> bool: | |
| letters = [c for c in text if c.isalpha()] | |
| if len(letters) >= 40: | |
| if sum(1 for c in letters if ord(c) > 0x24F) / len(letters) > 0.3: | |
| return False | |
| words = re.findall(r"[a-zA-Z']+", text.lower()) | |
| if len(words) < 20: | |
| return True | |
| return sum(w in _ENG for w in words) / len(words) >= 0.12 | |
| def strip_think(text: str) -> str: | |
| out = THINK.sub("", text) | |
| out = THINK_UNCLOSED.sub("", out) | |
| return out.strip() | |
| def sharegpt_to_messages(conversations: list[dict]) -> list[dict] | None: | |
| """ShareGPT -> messages, thinking stripped from assistant turns. | |
| Returns None if any assistant turn becomes empty after stripping.""" | |
| msgs = [] | |
| for m in conversations: | |
| role = ROLE.get(m["from"]) | |
| if role is None: | |
| return None | |
| content = m["value"] | |
| if role == "assistant": | |
| content = strip_think(content) | |
| if not content: | |
| return None | |
| msgs.append({"role": role, "content": content}) | |
| return msgs | |