Instructions to use matorus/replit-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use matorus/replit-coder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="matorus/replit-coder", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("matorus/replit-coder", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("matorus/replit-coder", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use matorus/replit-coder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "matorus/replit-coder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "matorus/replit-coder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/matorus/replit-coder
- SGLang
How to use matorus/replit-coder 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 "matorus/replit-coder" \ --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": "matorus/replit-coder", "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 "matorus/replit-coder" \ --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": "matorus/replit-coder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use matorus/replit-coder with Docker Model Runner:
docker model run hf.co/matorus/replit-coder
Upload folder using huggingface_hub
Browse files- config.json +1 -1
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -46,7 +46,7 @@
|
|
| 46 |
"resid_pdrop": 0,
|
| 47 |
"tokenizer_name": "replit/replit-code-v1-3b",
|
| 48 |
"torch_dtype": "bfloat16",
|
| 49 |
-
"transformers_version": "4.
|
| 50 |
"use_cache": true,
|
| 51 |
"verbose": 0,
|
| 52 |
"vocab_size": 32768
|
|
|
|
| 46 |
"resid_pdrop": 0,
|
| 47 |
"tokenizer_name": "replit/replit-code-v1-3b",
|
| 48 |
"torch_dtype": "bfloat16",
|
| 49 |
+
"transformers_version": "4.30.2",
|
| 50 |
"use_cache": true,
|
| 51 |
"verbose": 0,
|
| 52 |
"vocab_size": 32768
|
generation_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
-
"transformers_version": "4.
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
+
"transformers_version": "4.30.2"
|
| 5 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5201332505
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8613e8eed63df3169403f64545795a6712190c3c83bddc3a997024a28568532
|
| 3 |
size 5201332505
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"auto_map": {
|
| 3 |
"AutoTokenizer": [
|
| 4 |
-
"replit_lm_tokenizer.ReplitLMTokenizer",
|
| 5 |
null
|
| 6 |
]
|
| 7 |
},
|
|
|
|
| 1 |
{
|
| 2 |
"auto_map": {
|
| 3 |
"AutoTokenizer": [
|
| 4 |
+
"replit/replit-code-v1-3b--replit_lm_tokenizer.ReplitLMTokenizer",
|
| 5 |
null
|
| 6 |
]
|
| 7 |
},
|