Instructions to use T145/KRONOS-8B-V1-P1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use T145/KRONOS-8B-V1-P1 with Transformers:

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

pipe = pipeline("text-generation", model="T145/KRONOS-8B-V1-P1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("T145/KRONOS-8B-V1-P1")
model = AutoModelForCausalLM.from_pretrained("T145/KRONOS-8B-V1-P1")
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 T145/KRONOS-8B-V1-P1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "T145/KRONOS-8B-V1-P1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "T145/KRONOS-8B-V1-P1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/T145/KRONOS-8B-V1-P1

SGLang

How to use T145/KRONOS-8B-V1-P1 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 "T145/KRONOS-8B-V1-P1" \
    --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": "T145/KRONOS-8B-V1-P1",
		"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 "T145/KRONOS-8B-V1-P1" \
        --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": "T145/KRONOS-8B-V1-P1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use T145/KRONOS-8B-V1-P1 with Docker Model Runner:
```
docker model run hf.co/T145/KRONOS-8B-V1-P1
```

KRONOS-8B-V1-P1 / README.md

T145

Adding Evaluation Results (#1)

3c83c14 verified over 1 year ago

preview code

raw

history blame contribute delete

4.24 kB

metadata

library_name: transformers
tags:
  - merge
  - llama-3.1
  - roleplay
  - function calling
base_model:
  - unsloth/Meta-Llama-3.1-8B-Instruct
  - yuriachermann/Not-so-bright-AGI-Llama3.1-8B-UC200k-v2
datasets:
  - HuggingFaceH4/ultrachat_200k
base_model_relation: merge
model-index:
  - name: KRONOS-8B-V1-P1
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: wis-k/instruction-following-eval
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 78.5
            name: averaged accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FKRONOS-8B-V1-P1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: SaylorTwift/bbh
          split: test
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 29.97
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FKRONOS-8B-V1-P1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: lighteval/MATH-Hard
          split: test
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 18.96
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FKRONOS-8B-V1-P1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 6.04
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FKRONOS-8B-V1-P1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 8.48
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FKRONOS-8B-V1-P1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 30.67
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FKRONOS-8B-V1-P1
          name: Open LLM Leaderboard

KRONOS 8B V1 P1

This is a merge of Meta Llama 3.1 Instruct and the "Not so Bright" LORA, created using llm-tools.

The primary purpose of this model is to be merged into other models in the same family using the TIES merge method.

Creating quants for this is entirely unnecessary.

Merge Details

Configuration

The following Bash command was used to produce this model:

python /llm-tools/merge-lora.py -m unsloth/Meta-Llama-3.1-8B-Instruct -l yuriachermann/Not-so-bright-AGI-Llama3.1-8B-UC200k-v2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	28.77
IFEval (0-Shot)	78.50
BBH (3-Shot)	29.97
MATH Lvl 5 (4-Shot)	18.96
GPQA (0-shot)	6.04
MuSR (0-shot)	8.48
MMLU-PRO (5-shot)	30.67