Files
ModelHub XC a6c7d25257 初始化项目,由ModelHub XC社区提供模型
Model: indischepartij/TinyUltra-4x1.1B-Base-Alpha
Source: Original Platform
2026-05-10 07:25:02 +08:00

8.5 KiB

license, tags, model-index, widget
license tags model-index widget
cc-by-nc-4.0
moe
merge
mergekit
name results
TinyUltra-4x1.1B-Base-Alpha
task dataset metrics source
type name
text-generation Text Generation
name type config split args
AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test
num_few_shot
25
type value name
acc_norm 34.9 normalized accuracy
url name
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha Open LLM Leaderboard
task dataset metrics source
type name
text-generation Text Generation
name type split args
HellaSwag (10-Shot) hellaswag validation
num_few_shot
10
type value name
acc_norm 61.42 normalized accuracy
url name
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha Open LLM Leaderboard
task dataset metrics source
type name
text-generation Text Generation
name type config split args
MMLU (5-Shot) cais/mmlu all test
num_few_shot
5
type value name
acc 25.42 accuracy
url name
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha Open LLM Leaderboard
task dataset metrics source
type name
text-generation Text Generation
name type config split args
TruthfulQA (0-shot) truthful_qa multiple_choice validation
num_few_shot
0
type value
mc2 37.59
url name
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha Open LLM Leaderboard
task dataset metrics source
type name
text-generation Text Generation
name type config split args
Winogrande (5-shot) winogrande winogrande_xl validation
num_few_shot
5
type value name
acc 65.75 accuracy
url name
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha Open LLM Leaderboard
task dataset metrics source
type name
text-generation Text Generation
name type config split args
GSM8k (5-shot) gsm8k main test
num_few_shot
5
type value name
acc 2.58 accuracy
url name
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha Open LLM Leaderboard
example_title messages output
Pirate!
role content
system You are a pirate chatbot who always responds with Arr!
role content
user There's a llama on my lawn, how can I get rid of him?
text
Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare sight, but I've got a plan that might help ye get rid of 'im. Ye'll need to gather some carrots and hay, and then lure the llama away with the promise of a tasty treat. Once he's gone, ye can clean up yer lawn and enjoy the peace and quiet once again. But beware, me hearty, for there may be more llamas where that one came from! Arr!

image/jpeg

TinyUltra-4x1.1B-Base-Alpha

TinyUltra-4x1.1B-Base-Alpha is a Mixure of Experts (MoE) made with the following models using MergeKit:

Modelfile/Prompt format

SYSTEM You are a TinyUltra, helpful and lovely AI assistant.

TEMPLATE <|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>

PARAMETER stop <|system|>
PARAMETER stop <|user|>
PARAMETER stop <|assistant|>
PARAMETER stop </s>

🧩 Configuration

base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
gate_mode: hidden
dtype: float16
experts:
  - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
    positive_prompts:
    - "Help me debug this code."
    - "Rewrite this function in Python."
    - "Optimize this C# script."
    - "Implement this feature using JavaScript."
    - "Convert this HTML structure into a more efficient design."
    - "Assist me with writing a program that"
  - source_model: vihangd/DopeyTinyLlama-1.1B-v1
    positive_prompts:
    - "How do you"
    - "Explain the concept of"
    - "Give an overview of"
    - "Compare and contrast between"
    - "Provide information about"
    - "Help me understand"
    - "Summarize"
    - "Make a recommendation on"
    - "Answer this question"
  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
    positive_prompts:
    - "Write a program to solve this problem"
    - "Modify this function to improve its performance"
    - "Refactor this code to enhance readability"
    - "Create a custom function for this specific use case"
    - "Optimize this algorithm to reduce computational complexity"
    - "Implement this feature by extending existing codebase"
    - "Integrate this API call into the application"
    - "Help me troubleshoot and fix this bug"
    - "Review and test this code snippet before deployment"
    - "Analyze this error log to identify potential issues"
    - "Generate a set of unit tests for this module"
    - "Evaluate different approaches to solving this problem"
    - "Do a web search for"
    - "Use the plugin to"
  - source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
    positive_prompts:
    - "add these numbers"
    - "whats 2+2"
    - "subtraction"
    - "division"
    - "multiplication"
    - "addition"
    - "I need help with a math problem"
    - "Solve for x"
    - "Add these two numbers together: 4 + 3 = 7"
    - "Multiply 5 by 6: 5 * 6 = 30"
    - "Divide 8 by 2: 8 / 2 = 4"
    - "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
    - "Calculate the square root of 16: sqrt(16) = 4"
    - "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
    - "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
    - "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
    - "Graph the line y = 2x + 3"
    - "Approximate pi to three decimal places: 3.142"
    - "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
    - "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
    - "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
    - "Solve the system of equations Ax = b: x = [-5, 10]"
    - "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gmonsoon/TinyUltra-4x1.1B-Base-Alpha"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

GGUF: https://huggingface.co/indischepartij/TinyUltra-4x1.1B-Base-Alpha-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 37.94
AI2 Reasoning Challenge (25-Shot) 34.90
HellaSwag (10-Shot) 61.42
MMLU (5-Shot) 25.42
TruthfulQA (0-shot) 37.59
Winogrande (5-shot) 65.75
GSM8k (5-shot) 2.58