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

language	license	tags	base_model	datasets	model-index	new_version
en	llama3.2	text-generation-inference transformers llama trl sft reasoning llama-3	chuanli11/Llama-3.2-3B-Instruct-uncensored	KingNish/reasoning-base-20k lunahr/thea-name-overrides	name results thea-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 73.44 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-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 22.55 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-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 16.31 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-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 2.35 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-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 3.57 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-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 24.25 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=lunahr/thea-3b-25r Open LLM Leaderboard	lunahr/thea-3b-50r-u1

Model Description

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

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-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: chuanli11/Llama-3.2-3B-Instruct-uncensored
• 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.