language, license, tags, base_model, datasets, model-index

language	license	tags	base_model	datasets	model-index
en	llama3.2	text-generation-inference transformers llama trl sft reasoning llama-3	SicariusSicariiStuff/Impish_LLAMA_3B	KingNish/reasoning-base-20k lunahr/thea-name-overrides	name results thea-rp-3b-25r task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 65.78 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 20.01 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 11.71 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 3.24 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 5.93 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 22.89 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-rp-3b-25r Open LLM Leaderboard

Model Description

An uncensored roleplay reasoning Llama 3.2 3B model trained on reasoning data.

It may potentially be a highest scoring RP finetune of Llama 3.2.

It has been trained using improved training code, and gives an improved performance. Here is what inference code you should use:

from transformers import AutoModelForCausalLM, AutoTokenizer

MAX_REASONING_TOKENS = 1024
MAX_RESPONSE_TOKENS = 512

model_name = "lunahr/thea-rp-3b-25r"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Which is greater 9.9 or 9.11 ??"
messages = [
    {"role": "user", "content": prompt}
]

# Generate reasoning
reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("REASONING: " + reasoning_output)

# Generate answer
messages.append({"role": "reasoning", "content": reasoning_output})
response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("ANSWER: " + response_output)

• Trained by: Piotr Zalewski
• License: llama3.2
• Finetuned from model: SicariusSicariiStuff/Impish_LLAMA_3B
• Dataset used: KingNish/reasoning-base-20k

This Llama model was trained faster than Unsloth using custom training code.

Visit https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4 to find out how you can finetune your models using BOTH of the Kaggle provided GPUs.