modules: ['10_attn.q', '10_attn.v', '12_attn.o', '13_attn.q', '13_attn.v', '14_attn.k', '15_attn.k', '15_attn.v', '16_attn.o', '17_attn.o', '17_attn.q', '17_attn.v', '18_attn.k', '18_attn.q', '20_attn.v', '21_attn.k', '21_attn.v', '22_attn.v', '23_attn.v', '24_attn.k', '24_attn.o', '24_attn.q', '26_attn.k', '27_attn.o', '28_attn.q', '30_attn.o', '3_attn.k', '4_attn.o', '4_attn.v', '7_attn.q', '7_attn.v', '8_attn.k', '9_attn.k']

tags: ['model: llama_chat', 'repo_name: llama_chat_block_2_abstract_narrative_understanding_Community', 'file_name: llama_chat_block_2_abstract_narrative_understanding_Community_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: block', 'community: 2', 'pruning_ratio: 20', 'dataset_label: abstract_narrative_understanding', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'abstract_narrative_understanding']", 'finetune: Community', 'modules_size: 33', "modules: ['10_attn.q', '10_attn.v', '12_attn.o', '13_attn.q', '13_attn.v', '14_attn.k', '15_attn.k', '15_attn.v', '16_attn.o', '17_attn.o', '17_attn.q', '17_attn.v', '18_attn.k', '18_attn.q', '20_attn.v', '21_attn.k', '21_attn.v', '22_attn.v', '23_attn.v', '24_attn.k', '24_attn.o', '24_attn.q', '26_attn.k', '27_attn.o', '28_attn.q', '30_attn.o', '3_attn.k', '4_attn.o', '4_attn.v', '7_attn.q', '7_attn.v', '8_attn.k', '9_attn.k']", 'rank: 1']

Model card Files Files and versions

xet

Community

Instructions to use KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community with Transformers:

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

pipe = pipeline("text-generation", model="KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community")
model = AutoModelForCausalLM.from_pretrained("KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community

SGLang

How to use KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community 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/llama_chat_block_2_abstract_narrative_understanding_Community" \
    --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/llama_chat_block_2_abstract_narrative_understanding_Community",
		"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/llama_chat_block_2_abstract_narrative_understanding_Community" \
        --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/llama_chat_block_2_abstract_narrative_understanding_Community",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community with Docker Model Runner:
```
docker model run hf.co/KBhandari11/llama_chat_block_2_abstract_narrative_understanding_Community
```

New discussion

Resources

View closed (0)

Welcome to the community

The community tab is the place to discuss and collaborate with the HF community!