modules: ['7_mlp.down', '11_attn.k', '21_mlp.up', '10_attn.q', '22_mlp.down', '16_gate', '28_attn.q', '4_attn.k', '3_attn.o', '15_attn.o', '23_gate', '16_mlp.up', '6_attn.o', '6_attn.v', '29_mlp.up', '25_attn.v', '17_attn.q', '18_mlp.up', '13_mlp.up', '26_attn.q', '9_attn.k', '16_mlp.down', '22_attn.o', '25_mlp.down', '17_attn.v', '20_gate', '3_mlp.down', '11_gate']

tags: ['model: llama', 'repo_name: llama_block_2_gre_reading_comprehension_Complete Random', 'file_name: llama_block_2_gre_reading_comprehension_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: block', 'community: 2', 'pruning_ratio: 20', 'dataset_label: gre_reading_comprehension', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'gre_reading_comprehension']", 'finetune: Complete Random', 'modules_size: 28', "modules: ['7_mlp.down', '11_attn.k', '21_mlp.up', '10_attn.q', '22_mlp.down', '16_gate', '28_attn.q', '4_attn.k', '3_attn.o', '15_attn.o', '23_gate', '16_mlp.up', '6_attn.o', '6_attn.v', '29_mlp.up', '25_attn.v', '17_attn.q', '18_mlp.up', '13_mlp.up', '26_attn.q', '9_attn.k', '16_mlp.down', '22_attn.o', '25_mlp.down', '17_attn.v', '20_gate', '3_mlp.down', '11_gate']", 'rank: 1']

Model card Files Files and versions

xet

Community

Instructions to use KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random with Transformers:

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

pipe = pipeline("text-generation", model="KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random")
model = AutoModelForCausalLM.from_pretrained("KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KBhandari11/llama_block_2_gre_reading_comprehension_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/llama_block_2_gre_reading_comprehension_Complete_Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random

SGLang

How to use KBhandari11/llama_block_2_gre_reading_comprehension_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/llama_block_2_gre_reading_comprehension_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/llama_block_2_gre_reading_comprehension_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/llama_block_2_gre_reading_comprehension_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/llama_block_2_gre_reading_comprehension_Complete_Random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random with Docker Model Runner:
```
docker model run hf.co/KBhandari11/llama_block_2_gre_reading_comprehension_Complete_Random
```

llama_block_2_gre_reading_comprehension_Complete_Random / config.json

KBhandari11

Upload LlamaForCausalLM

eae427a verified about 1 year ago

Raw

History Blame Contribute Delete

677 Bytes

	{
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 32,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.52.4",
	"use_cache": true,
	"vocab_size": 32000
	}