modules: ['13_attn.k', '17_attn.v', '6_attn.v', '21_attn.o', '11_mlp.up', '15_gate', '17_attn.k', '29_attn.v', '10_gate', '16_attn.v', '29_mlp.up', '7_mlp.down', '29_attn.o', '5_gate', '22_gate', '3_gate', '4_attn.v', '5_attn.k', '11_attn.o', '19_gate', '26_mlp.up', '3_attn.q', '28_attn.k']

tags: ['model: vicuna', 'repo_name: vicuna_block_3_philosophy_Complete Random', 'file_name: vicuna_block_3_philosophy_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 3', 'pruning_ratio: 20', 'dataset_label: philosophy', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'philosophy']", 'finetune: Complete Random', 'modules_size: 23', "modules: ['13_attn.k', '17_attn.v', '6_attn.v', '21_attn.o', '11_mlp.up', '15_gate', '17_attn.k', '29_attn.v', '10_gate', '16_attn.v', '29_mlp.up', '7_mlp.down', '29_attn.o', '5_gate', '22_gate', '3_gate', '4_attn.v', '5_attn.k', '11_attn.o', '19_gate', '26_mlp.up', '3_attn.q', '28_attn.k']", 'rank: 2']

Model card Files Files and versions

xet

Community

Instructions to use KBhandari11/vicuna_block_3_philosophy_Complete_Random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use KBhandari11/vicuna_block_3_philosophy_Complete_Random with Transformers:

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

pipe = pipeline("text-generation", model="KBhandari11/vicuna_block_3_philosophy_Complete_Random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KBhandari11/vicuna_block_3_philosophy_Complete_Random")
model = AutoModelForCausalLM.from_pretrained("KBhandari11/vicuna_block_3_philosophy_Complete_Random")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KBhandari11/vicuna_block_3_philosophy_Complete_Random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KBhandari11/vicuna_block_3_philosophy_Complete_Random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KBhandari11/vicuna_block_3_philosophy_Complete_Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KBhandari11/vicuna_block_3_philosophy_Complete_Random

SGLang

How to use KBhandari11/vicuna_block_3_philosophy_Complete_Random 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 "KBhandari11/vicuna_block_3_philosophy_Complete_Random" \
    --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": "KBhandari11/vicuna_block_3_philosophy_Complete_Random",
		"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 "KBhandari11/vicuna_block_3_philosophy_Complete_Random" \
        --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": "KBhandari11/vicuna_block_3_philosophy_Complete_Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KBhandari11/vicuna_block_3_philosophy_Complete_Random with Docker Model Runner:
```
docker model run hf.co/KBhandari11/vicuna_block_3_philosophy_Complete_Random
```

vicuna_block_3_philosophy_Complete_Random

Commit History

Upload LlamaForCausalLM

59e458b
verified

KBhandari11 commited on Jun 2, 2025

initial commit

7bdfd59
verified

KBhandari11 commited on Jun 2, 2025

Commit History

Upload LlamaForCausalLM 59e458b verified

initial commit 7bdfd59 verified

Upload LlamaForCausalLM

59e458b
verified

initial commit

7bdfd59
verified