Instructions to use weblab-GENIAC/team_kawagoshi_submit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use weblab-GENIAC/team_kawagoshi_submit with Transformers:

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

pipe = pipeline("text-generation", model="weblab-GENIAC/team_kawagoshi_submit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("weblab-GENIAC/team_kawagoshi_submit")
model = AutoModelForCausalLM.from_pretrained("weblab-GENIAC/team_kawagoshi_submit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use weblab-GENIAC/team_kawagoshi_submit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "weblab-GENIAC/team_kawagoshi_submit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weblab-GENIAC/team_kawagoshi_submit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/weblab-GENIAC/team_kawagoshi_submit

SGLang

How to use weblab-GENIAC/team_kawagoshi_submit 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 "weblab-GENIAC/team_kawagoshi_submit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weblab-GENIAC/team_kawagoshi_submit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "weblab-GENIAC/team_kawagoshi_submit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weblab-GENIAC/team_kawagoshi_submit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use weblab-GENIAC/team_kawagoshi_submit with Docker Model Runner:
```
docker model run hf.co/weblab-GENIAC/team_kawagoshi_submit
```

final_merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using kawagoshi-llm-team/llma3_manydata_our_data_rope as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: kawagoshi-llm-team/llma3_manydata_our_data_rope
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 8]
    model: kawagoshi-llm-team/llma3_manydata_our_data_rope
    parameters:
      density: 0.7653375506603464
      weight: 0.13767610478325062
  - layer_range: [0, 8]
    model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope
    parameters:
      density: 0.7336602489449524
      weight: 0.3666639544856324
  - layer_range: [0, 8]
    model: kawagoshi-llm-team/llama3_sft_many_chat
    parameters:
      density: 1.0
      weight: 0.3030835610677404
- sources:
  - layer_range: [8, 16]
    model: kawagoshi-llm-team/llma3_manydata_our_data_rope
    parameters:
      density: 0.9861387586510485
      weight: 0.3948174181228292
  - layer_range: [8, 16]
    model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope
    parameters:
      density: 0.8413699662162298
      weight: 0.45739982954282526
  - layer_range: [8, 16]
    model: kawagoshi-llm-team/llama3_sft_many_chat
    parameters:
      density: 1.0
      weight: 0.30274586211044396
- sources:
  - layer_range: [16, 24]
    model: kawagoshi-llm-team/llma3_manydata_our_data_rope
    parameters:
      density: 0.9503146891835705
      weight: 0.2849061463174477
  - layer_range: [16, 24]
    model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope
    parameters:
      density: 0.832031377573231
      weight: 0.6047693096979141
  - layer_range: [16, 24]
    model: kawagoshi-llm-team/llama3_sft_many_chat
    parameters:
      density: 0.9442991059236329
      weight: 0.4002445342115458
- sources:
  - layer_range: [24, 32]
    model: kawagoshi-llm-team/llma3_manydata_our_data_rope
    parameters:
      density: 0.8517897851608993
      weight: 0.3362716927810899
  - layer_range: [24, 32]
    model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope
    parameters:
      density: 1.0
      weight: 0.2909336827183003
  - layer_range: [24, 32]
    model: kawagoshi-llm-team/llama3_sft_many_chat
    parameters:
      density: 1.0
      weight: 0.3474712168573882
- sources:
  - layer_range: [32, 40]
    model: kawagoshi-llm-team/llma3_manydata_our_data_rope
    parameters:
      density: 1.0
      weight: 0.27727322046805786
  - layer_range: [32, 40]
    model: kawagoshi-llm-team/llma3_manydata_not_our_data_rope
    parameters:
      density: 0.8394275769864135
      weight: 0.4724670213437233
  - layer_range: [32, 40]
    model: kawagoshi-llm-team/llama3_sft_many_chat
    parameters:
      density: 1.0
      weight: 0.31333702280148296
tokenizer_source: base

Downloads last month: 5

Safetensors

Model size

12B params

Tensor type

BF16

Space using weblab-GENIAC/team_kawagoshi_submit 1

Papers for weblab-GENIAC/team_kawagoshi_submit

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 33

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19