Instructions to use Rudra-ai/code-llama-2-7b-instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rudra-ai/code-llama-2-7b-instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="Rudra-ai/code-llama-2-7b-instruct-hf", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rudra-ai/code-llama-2-7b-instruct-hf", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Rudra-ai/code-llama-2-7b-instruct-hf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rudra-ai/code-llama-2-7b-instruct-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rudra-ai/code-llama-2-7b-instruct-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rudra-ai/code-llama-2-7b-instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rudra-ai/code-llama-2-7b-instruct-hf

SGLang

How to use Rudra-ai/code-llama-2-7b-instruct-hf 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 "Rudra-ai/code-llama-2-7b-instruct-hf" \
    --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": "Rudra-ai/code-llama-2-7b-instruct-hf",
		"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 "Rudra-ai/code-llama-2-7b-instruct-hf" \
        --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": "Rudra-ai/code-llama-2-7b-instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rudra-ai/code-llama-2-7b-instruct-hf with Docker Model Runner:
```
docker model run hf.co/Rudra-ai/code-llama-2-7b-instruct-hf
```

Rudra-ai commited on Aug 28, 2023

Commit

cb4da83

1 Parent(s): 408e983

Update config.json

Browse files

Files changed (1) hide show

config.json +8 -1

config.json CHANGED Viewed

@@ -21,5 +21,12 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.32.0",
   "use_cache": true,
-  "vocab_size": 32016
 }

   "torch_dtype": "bfloat16",
   "transformers_version": "4.32.0",
   "use_cache": true,
+  "vocab_size": 32016,
+  "auto_map": {
+        "AutoConfig": "configuration_llama.LlamaConfig",
+        "AutoModel": "modeling_llama.LlamaModel",
+        "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM",
+        "AutoModelForSequenceClassification": "modeling_llama.LlamaForSequenceClassification"
+    },
+  "pad_token_id": 0
 }