Instructions to use CarperAI/diff-codegen-350m-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CarperAI/diff-codegen-350m-v2 with Transformers:

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

pipe = pipeline("text-generation", model="CarperAI/diff-codegen-350m-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CarperAI/diff-codegen-350m-v2")
model = AutoModelForCausalLM.from_pretrained("CarperAI/diff-codegen-350m-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CarperAI/diff-codegen-350m-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CarperAI/diff-codegen-350m-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CarperAI/diff-codegen-350m-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CarperAI/diff-codegen-350m-v2

SGLang

How to use CarperAI/diff-codegen-350m-v2 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 "CarperAI/diff-codegen-350m-v2" \
    --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": "CarperAI/diff-codegen-350m-v2",
		"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 "CarperAI/diff-codegen-350m-v2" \
        --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": "CarperAI/diff-codegen-350m-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CarperAI/diff-codegen-350m-v2 with Docker Model Runner:
```
docker model run hf.co/CarperAI/diff-codegen-350m-v2
```

Upload config.json

by HyperionHF - opened Jan 23, 2023

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

+42

-0

Files changed (1) hide show

config.json +42 -0

config.json ADDED Viewed

	@@ -0,0 +1,42 @@

+{
+  "_name_or_path": "codegen-350",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.22.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50295
+}