Instructions to use codellama/CodeLlama-34b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codellama/CodeLlama-34b-hf with Transformers:

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

pipe = pipeline("text-generation", model="codellama/CodeLlama-34b-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-34b-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-34b-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codellama/CodeLlama-34b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codellama/CodeLlama-34b-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-34b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codellama/CodeLlama-34b-hf

SGLang

How to use codellama/CodeLlama-34b-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-34b-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": "codellama/CodeLlama-34b-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 "codellama/CodeLlama-34b-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": "codellama/CodeLlama-34b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codellama/CodeLlama-34b-hf with Docker Model Runner:
```
docker model run hf.co/codellama/CodeLlama-34b-hf
```

Upload tokenizer

#15

by ArthurZ HF Staff - opened Sep 14, 2023

base: refs/heads/main

←

from: refs/pr/15

Discussion Files changed

+12

-6

Files changed (2) hide show

tokenizer.json +3 -3
tokenizer_config.json +9 -3

tokenizer.json CHANGED Viewed

@@ -9,7 +9,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
       "special": true
     },
     {
@@ -18,7 +18,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
       "special": true
     },
     {
@@ -27,7 +27,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
       "special": true
     }
   ],

       "single_word": false,
       "lstrip": false,
       "rstrip": false,
+      "normalized": true,
       "special": true
     },
     {
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
+      "normalized": true,
       "special": true
     },
     {
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
+      "normalized": true,
       "special": true
     }
   ],

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,5 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "bos_token": {
     "__type": "AddedToken",
     "content": "<s>",
@@ -18,10 +17,16 @@
     "rstrip": false,
     "single_word": false
   },
   "legacy": null,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
   "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
@@ -30,5 +35,6 @@
     "normalized": true,
     "rstrip": false,
     "single_word": false
-  }
 }

 {
+  "additional_special_tokens": [],
   "bos_token": {
     "__type": "AddedToken",
     "content": "<s>",
     "rstrip": false,
     "single_word": false
   },
+  "eot_token": null,
+  "fill_token": "<FILL_ME>",
   "legacy": null,
+  "middle_token": null,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
+  "prefix_token": null,
   "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": null,
   "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": {
     "__type": "AddedToken",
     "normalized": true,
     "rstrip": false,
     "single_word": false
+  },
+  "use_default_system_prompt": false
 }