Instructions to use ammarnasr/codegen2-1B-react with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ammarnasr/codegen2-1B-react with Transformers:

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

pipe = pipeline("text-generation", model="ammarnasr/codegen2-1B-react", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ammarnasr/codegen2-1B-react", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ammarnasr/codegen2-1B-react", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ammarnasr/codegen2-1B-react with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ammarnasr/codegen2-1B-react"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ammarnasr/codegen2-1B-react",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ammarnasr/codegen2-1B-react

SGLang

How to use ammarnasr/codegen2-1B-react 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 "ammarnasr/codegen2-1B-react" \
    --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": "ammarnasr/codegen2-1B-react",
		"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 "ammarnasr/codegen2-1B-react" \
        --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": "ammarnasr/codegen2-1B-react",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ammarnasr/codegen2-1B-react with Docker Model Runner:
```
docker model run hf.co/ammarnasr/codegen2-1B-react
```

ammarnasr commited on Jan 20, 2024

Commit

f55be2c

verified ·

1 Parent(s): 0279c48

Update config.json

Browse files

Files changed (1) hide show

config.json +7 -7

config.json CHANGED Viewed

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "Salesforce/codegen2-1B",
   "activation_function": "gelu_new",
   "architectures": [
     "CodeGenForCausalLM"
   ],
   "attn_pdrop": 0.0,
   "auto_map": {
-    "AutoConfig": "Salesforce/codegen2-1B--configuration_codegen.CodeGenConfig",
-    "AutoModel": "Salesforce/codegen2-1B--modeling_codegen.CodeGenModel",
-    "AutoModelForCausalLM": "Salesforce/codegen2-1B--modeling_codegen.CodeGenForCausalLM"
   },
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
@@ -26,6 +26,7 @@
   "n_positions": 2048,
   "resid_pdrop": 0.0,
   "rotary_dim": 64,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -42,8 +43,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
-  "trust_remote_code": true,
   "use_cache": true,
   "vocab_size": 51200
-}

 {
+  "_name_or_path": "checkpoints/codegen2-1B/",
   "activation_function": "gelu_new",
   "architectures": [
     "CodeGenForCausalLM"
   ],
   "attn_pdrop": 0.0,
   "auto_map": {
+    "AutoConfig": "configuration_codegen.CodeGenConfig",
+    "AutoModel": "modeling_codegen.CodeGenModel",
+    "AutoModelForCausalLM": "modeling_codegen.CodeGenForCausalLM"
   },
   "bos_token_id": 1,
   "embd_pdrop": 0.0,
   "n_positions": 2048,
   "resid_pdrop": 0.0,
   "rotary_dim": 64,
+ "trust_remote_code":true,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
   "use_cache": true,
   "vocab_size": 51200
+}