Instructions to use replit/replit-code-v1_5-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use replit/replit-code-v1_5-3b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="replit/replit-code-v1_5-3b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("replit/replit-code-v1_5-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("replit/replit-code-v1_5-3b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use replit/replit-code-v1_5-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "replit/replit-code-v1_5-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "replit/replit-code-v1_5-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/replit/replit-code-v1_5-3b

SGLang

How to use replit/replit-code-v1_5-3b 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 "replit/replit-code-v1_5-3b" \
    --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": "replit/replit-code-v1_5-3b",
		"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 "replit/replit-code-v1_5-3b" \
        --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": "replit/replit-code-v1_5-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use replit/replit-code-v1_5-3b with Docker Model Runner:
```
docker model run hf.co/replit/replit-code-v1_5-3b
```

Update README.md

by madhavatreplit - opened Oct 11, 2023

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

+18

-5

Files changed (1) hide show

README.md +18 -5

README.md CHANGED Viewed

@@ -1,5 +1,16 @@
 ---
 license: apache-2.0
 ---
 # Replit Code V-1.5 3B
@@ -10,13 +21,16 @@ Developed by: Replit, Inc.
 Replit Code v1.5 is a 3.3B parameter Causal Language Model focused on **Code Completion**.
-The model is trained in `bfloat16` on 1T tokens of code (~200B tokens  over 5 epochs, including linear cooldown) for 30 programming languages from a subset of permissively licensed code from Bigcode's [Stack Dedup V2 dataset](https://huggingface.co/datasets/bigcode/the-stack-dedup) and a dev-oriented samples from StackExchange.
-The context size is 4096 tokens can be extended using techniques on its ALiBi positional embeddings.
-We use the GPTNeoX tokenizer with a custom trained and optimized vocabulary of 32768 tokens. This custom vocabulary led to single-digit % points on compression while maintaining or improving coverage on our training corpus.
-The model has been trained on the [MosaicML](https://www.mosaicml.com/) platform on 128  H100-80GB GPUs.
 ## Dependancies
 You will need to install the latest versions of the following dependencies:
@@ -85,6 +99,5 @@ Replit intends this model be used by anyone as a foundational model for applicat
 The model is trained specifically for code completion tasks.
 ## Limitations
 The pre-training dataset may have contained offensive or inappropriate content even after applying data cleansing and toxicity and profanity filters, and such content may be reflected in model generated text. We recommend that users exercise reasonable caution when using in production systems. Do not use for any applications that may cause harm or distress to individuals or groups.

 ---
 license: apache-2.0
+datasets:
+  - bigcode/the-stack-dedup
+  - togethercomputer/RedPajama-Data-1T
+tags:
+  - code
+  - Composer
+  - MosaicML
+  - llm-foundry
+  - StreamingDatasets
+language:
+  - code
 ---
 # Replit Code V-1.5 3B
 Replit Code v1.5 is a 3.3B parameter Causal Language Model focused on **Code Completion**.
+The model is trained in `bfloat16` on 1T tokens of code (~200B tokens  over 5 epochs, including linear cooldown) for 30 programming languages from a subset of permissively licensed code from Bigcode's [Stack Dedup dataset](https://huggingface.co/datasets/bigcode/the-stack-dedup), a filtered natural language sample from Markdown and reStructuredText subsets from the same Stack Dedup dataset, and a dev-oriented sample from  [RedPajama's StackExchange dataset](https://github.com/togethercomputer/RedPajama-Data) sourced from the [Stack Exchange Data Dump by Stack Exchange Inc](https://archive.org/details/stackexchange).
+The 30 programming languages are:
+```
+Java, JavaScript, C, PHP, Python, C++, C#, TypeScript, Go, CSS, HTML, Rust, Ruby, Swift, Scala, Shell, Lua, Perl, Haskell, JSX, Julia, Common Lisp, OCaml, Solidity, Scheme, R, Zig, SQL, Racket, D
+```
+The context size of the model is 4096 tokens. We use the GPTNeoX tokenizer with a custom trained and optimized vocabulary of 32768 tokens. This custom vocabulary led to single-digit % points on compression while maintaining or improving coverage on our training corpus.
+The model has been trained on the [MosaicML](https://www.mosaicml.com/) platform on 128  H100-80GB GPUs using their [LLM Foundry](https://github.com/mosaicml/llm-foundry) and [Composer](https://github.com/mosaicml/composer) training library built on top of PyTorch.
 ## Dependancies
 You will need to install the latest versions of the following dependencies:
 The model is trained specifically for code completion tasks.
 ## Limitations
 The pre-training dataset may have contained offensive or inappropriate content even after applying data cleansing and toxicity and profanity filters, and such content may be reflected in model generated text. We recommend that users exercise reasonable caution when using in production systems. Do not use for any applications that may cause harm or distress to individuals or groups.