Text Generation
Transformers
PyTorch
English
shram
research
sparse-attention
mixture-of-experts
custom_code
Instructions to use smithblack-0/SHRAM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use smithblack-0/SHRAM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="smithblack-0/SHRAM", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("smithblack-0/SHRAM", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use smithblack-0/SHRAM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "smithblack-0/SHRAM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "smithblack-0/SHRAM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/smithblack-0/SHRAM
- SGLang
How to use smithblack-0/SHRAM 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 "smithblack-0/SHRAM" \ --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": "smithblack-0/SHRAM", "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 "smithblack-0/SHRAM" \ --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": "smithblack-0/SHRAM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use smithblack-0/SHRAM with Docker Model Runner:
docker model run hf.co/smithblack-0/SHRAM
Update architecture and tokenizer
Browse files- config.json +1 -1
- huggingface.py +0 -0
config.json
CHANGED
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"rope_mode": "main_sequence",
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"training_sequence_length": 1024,
|
| 26 |
-
"transformers_version": "5.
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 50277,
|
| 29 |
"window_size": 128
|
|
|
|
| 23 |
"rope_mode": "main_sequence",
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"training_sequence_length": 1024,
|
| 26 |
+
"transformers_version": "5.9.0",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 50277,
|
| 29 |
"window_size": 128
|
huggingface.py
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|