Instructions to use Jagdishram/test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jagdishram/test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jagdishram/test")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jagdishram/test") model = AutoModelForCausalLM.from_pretrained("Jagdishram/test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jagdishram/test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jagdishram/test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jagdishram/test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jagdishram/test
- SGLang
How to use Jagdishram/test 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 "Jagdishram/test" \ --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": "Jagdishram/test", "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 "Jagdishram/test" \ --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": "Jagdishram/test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jagdishram/test with Docker Model Runner:
docker model run hf.co/Jagdishram/test
Commit ·
78c359e
1
Parent(s): 04e06c7
Upload config
Browse files- config.json +0 -3
config.json
CHANGED
|
@@ -1,12 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "./saved_models_gpt-j-6B-8bit/gpt-j-6B",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPTJForCausalLM"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.0,
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
-
"eight_bit": true,
|
| 10 |
"embd_pdrop": 0.0,
|
| 11 |
"eos_token_id": 50256,
|
| 12 |
"gradient_checkpointing": false,
|
|
@@ -36,7 +34,6 @@
|
|
| 36 |
},
|
| 37 |
"tie_word_embeddings": false,
|
| 38 |
"tokenizer_class": "GPT2Tokenizer",
|
| 39 |
-
"torch_dtype": "float32",
|
| 40 |
"transformers_version": "4.25.1",
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50400
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPTJForCausalLM"
|
| 5 |
],
|
| 6 |
"attn_pdrop": 0.0,
|
| 7 |
"bos_token_id": 50256,
|
|
|
|
| 8 |
"embd_pdrop": 0.0,
|
| 9 |
"eos_token_id": 50256,
|
| 10 |
"gradient_checkpointing": false,
|
|
|
|
| 34 |
},
|
| 35 |
"tie_word_embeddings": false,
|
| 36 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
| 37 |
"transformers_version": "4.25.1",
|
| 38 |
"use_cache": true,
|
| 39 |
"vocab_size": 50400
|