base_IIXIV

Instructions to use mainline777/base_IIXIV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mainline777/base_IIXIV with Transformers:

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

pipe = pipeline("text-generation", model="mainline777/base_IIXIV", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mainline777/base_IIXIV", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mainline777/base_IIXIV with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mainline777/base_IIXIV"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mainline777/base_IIXIV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mainline777/base_IIXIV

SGLang

How to use mainline777/base_IIXIV 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 "mainline777/base_IIXIV" \
    --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": "mainline777/base_IIXIV",
		"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 "mainline777/base_IIXIV" \
        --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": "mainline777/base_IIXIV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mainline777/base_IIXIV with Docker Model Runner:
```
docker model run hf.co/mainline777/base_IIXIV
```

base_IIXIV / fla /ops /utils /__init__.py

mainline777

Duplicate from silx-ai/Quasar-Preview

41865df 26 days ago

Raw

History Blame Contribute Delete

1.44 kB

	from .cumsum import (
	chunk_global_cumsum,
	chunk_global_cumsum_scalar,
	chunk_global_cumsum_vector,
	chunk_local_cumsum,
	chunk_local_cumsum_scalar,
	chunk_local_cumsum_vector,
	)
	from .index import (
	get_max_num_splits,
	prepare_chunk_indices,
	prepare_chunk_offsets,
	prepare_cu_seqlens_from_lens,
	prepare_cu_seqlens_from_mask,
	prepare_lens,
	prepare_lens_from_mask,
	prepare_position_ids,
	prepare_sequence_ids,
	prepare_token_indices,
	)
	from .logsumexp import logsumexp_fwd
	from .matmul import addmm, matmul
	from .pack import pack_sequence, unpack_sequence
	from .pooling import mean_pooling
	from .softmax import softmax_bwd, softmax_fwd
	from .softplus import softplus
	from .solve_tril import solve_tril

	__all__ = [
	"addmm",
	"chunk_global_cumsum",
	"chunk_global_cumsum_scalar",
	"chunk_global_cumsum_vector",
	"chunk_local_cumsum",
	"chunk_local_cumsum_scalar",
	"chunk_local_cumsum_vector",
	"get_max_num_splits",
	"logsumexp_fwd",
	"matmul",
	"mean_pooling",
	"pack_sequence",
	"prepare_chunk_indices",
	"prepare_chunk_offsets",
	"prepare_cu_seqlens_from_lens",
	"prepare_cu_seqlens_from_mask",
	"prepare_lens",
	"prepare_lens_from_mask",
	"prepare_position_ids",
	"prepare_sequence_ids",
	"prepare_token_indices",
	"softmax_bwd",
	"softmax_fwd",
	"softplus",
	"solve_tril",
	"unpack_sequence",
	]