Instructions to use lamm-mit/SilkomeGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lamm-mit/SilkomeGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lamm-mit/SilkomeGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lamm-mit/SilkomeGPT") model = AutoModelForCausalLM.from_pretrained("lamm-mit/SilkomeGPT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lamm-mit/SilkomeGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lamm-mit/SilkomeGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lamm-mit/SilkomeGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lamm-mit/SilkomeGPT
- SGLang
How to use lamm-mit/SilkomeGPT 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 "lamm-mit/SilkomeGPT" \ --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": "lamm-mit/SilkomeGPT", "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 "lamm-mit/SilkomeGPT" \ --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": "lamm-mit/SilkomeGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lamm-mit/SilkomeGPT with Docker Model Runner:
docker model run hf.co/lamm-mit/SilkomeGPT
Delete SilkomeGPT
Browse files
SilkomeGPT/config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "lamm-mit/SilkomeGPT",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"GPTNeoXForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"bos_token_id": 0,
|
| 7 |
-
"classifier_dropout": 0.1,
|
| 8 |
-
"eos_token_id": 2,
|
| 9 |
-
"hidden_act": "gelu",
|
| 10 |
-
"hidden_size": 1024,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 4096,
|
| 13 |
-
"layer_norm_eps": 1e-05,
|
| 14 |
-
"max_position_embeddings": 2048,
|
| 15 |
-
"model_type": "gpt_neox",
|
| 16 |
-
"num_attention_heads": 8,
|
| 17 |
-
"num_hidden_layers": 12,
|
| 18 |
-
"rotary_emb_base": 10000,
|
| 19 |
-
"rotary_pct": 0.25,
|
| 20 |
-
"tie_word_embeddings": false,
|
| 21 |
-
"torch_dtype": "float32",
|
| 22 |
-
"transformers_version": "4.31.0.dev0",
|
| 23 |
-
"use_cache": false,
|
| 24 |
-
"use_parallel_residual": true,
|
| 25 |
-
"vocab_size": 50000
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SilkomeGPT/generation_config.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 0,
|
| 4 |
-
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.31.0.dev0",
|
| 6 |
-
"use_cache": false
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SilkomeGPT/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:52a8789f769c31a72cebd1cbe4711f547babbb50e8972599e0918044c4b2bb08
|
| 3 |
-
size 1014279309
|
|
|
|
|
|
|
|
|
|
|
|
SilkomeGPT/special_tokens_map.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "</s>",
|
| 3 |
-
"pad_token": "</s>"
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SilkomeGPT/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
SilkomeGPT/tokenizer_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"clean_up_tokenization_spaces": true,
|
| 3 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
-
"padding": "max_length",
|
| 5 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|