Instructions to use vikp/cleaner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikp/cleaner with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vikp/cleaner")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("vikp/cleaner") model = AutoModelForCausalLM.from_pretrained("vikp/cleaner") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use vikp/cleaner with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vikp/cleaner" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vikp/cleaner", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vikp/cleaner
- SGLang
How to use vikp/cleaner 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 "vikp/cleaner" \ --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": "vikp/cleaner", "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 "vikp/cleaner" \ --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": "vikp/cleaner", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vikp/cleaner with Docker Model Runner:
docker model run hf.co/vikp/cleaner
Upload FlashGPTNeoXForCausalLM
Browse files- config.json +4 -4
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 0,
|
|
@@ -15,8 +15,8 @@
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 2048,
|
| 17 |
"model_type": "gpt_neox",
|
| 18 |
-
"num_attention_heads":
|
| 19 |
-
"num_hidden_layers":
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"rope_scaling": {
|
| 22 |
"factor": 4.0,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-1.4b-deduped",
|
| 3 |
"architectures": [
|
| 4 |
+
"FlashGPTNeoXForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 0,
|
|
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 2048,
|
| 17 |
"model_type": "gpt_neox",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"rope_scaling": {
|
| 22 |
"factor": 4.0,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4cff9f2a3a6a3e04bc58f56ebdbf39e2ac88ec28f7c4e8aa19b711b71bc0b11
|
| 3 |
+
size 5658700617
|