Instructions to use codellama/CodeLlama-70b-Instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codellama/CodeLlama-70b-Instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="codellama/CodeLlama-70b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-70b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-70b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codellama/CodeLlama-70b-Instruct-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codellama/CodeLlama-70b-Instruct-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-70b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codellama/CodeLlama-70b-Instruct-hf

SGLang

How to use codellama/CodeLlama-70b-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 "codellama/CodeLlama-70b-Instruct-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-70b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "codellama/CodeLlama-70b-Instruct-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-70b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codellama/CodeLlama-70b-Instruct-hf with Docker Model Runner:
```
docker model run hf.co/codellama/CodeLlama-70b-Instruct-hf
```

Add <step> token, chat template

by pcuenq HF Staff - opened Jan 29, 2024

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

+23

-3

Files changed (3) hide show

added_tokens.json +3 -0
tokenizer.json +11 -3
tokenizer_config.json +9 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+  "<step>": 32015
+}

tokenizer.json CHANGED Viewed

@@ -29,6 +29,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
     }
   ],
   "normalizer": {
@@ -32149,8 +32158,7 @@
       "▁<EOT><EOT>": 32011,
       "▁<EOT><EOT><EOT>": 32012,
       "▁<EOT><EOT><EOT><EOT>": 32013,
-      "▁<EOT><EOT><EOT><EOT><EOT>": 32014,
-      "<step>": 32015
     },
     "merges": [
       "▁ t",
@@ -93415,4 +93423,4 @@
       "▁<EOT >"
     ]
   }
-}

       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32015,
+      "content": "<step>",
+      "single_word": true,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": false,
+      "special": false
     }
   ],
   "normalizer": {
       "▁<EOT><EOT>": 32011,
       "▁<EOT><EOT><EOT>": 32012,
       "▁<EOT><EOT><EOT><EOT>": 32013,
+      "▁<EOT><EOT><EOT><EOT><EOT>": 32014
     },
     "merges": [
       "▁ t",
       "▁<EOT >"
     ]
   }
+}

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,6 +26,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",

 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set user_index = 1 %}{% else %}{% set user_index = 0 %}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != ((loop.index0 + user_index) % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{{ '<s>' }}{% endif %}{% set content = 'Source: ' + message['role'] + '\n\n ' + message['content'].strip() %}{{ content + ' <step> ' }}{% endfor %}{{'Source: assistant\nDestination: user\n\n '}}",
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32015": {
+      "content": "<step>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": false
     }
   },
   "bos_token": "<s>",