Instructions to use Brandoko/CodeLlama-13b-Recharts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Brandoko/CodeLlama-13b-Recharts with Transformers:

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

pipe = pipeline("text-generation", model="Brandoko/CodeLlama-13b-Recharts")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Brandoko/CodeLlama-13b-Recharts")
model = AutoModelForCausalLM.from_pretrained("Brandoko/CodeLlama-13b-Recharts")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Brandoko/CodeLlama-13b-Recharts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Brandoko/CodeLlama-13b-Recharts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Brandoko/CodeLlama-13b-Recharts",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Brandoko/CodeLlama-13b-Recharts

SGLang

How to use Brandoko/CodeLlama-13b-Recharts 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 "Brandoko/CodeLlama-13b-Recharts" \
    --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": "Brandoko/CodeLlama-13b-Recharts",
		"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 "Brandoko/CodeLlama-13b-Recharts" \
        --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": "Brandoko/CodeLlama-13b-Recharts",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Brandoko/CodeLlama-13b-Recharts with Docker Model Runner:
```
docker model run hf.co/Brandoko/CodeLlama-13b-Recharts
```

Brandoko commited on Oct 7, 2023

Commit

0567343

1 Parent(s): c43fb12

Upload tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +0 -1
tokenizer.json +0 -0
tokenizer_config.json +10 -16

special_tokens_map.json CHANGED Viewed

@@ -7,6 +7,5 @@
   ],
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "pad_token": "</s>",
   "unk_token": "<unk>"
 }

   ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -1,28 +1,26 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -76,12 +74,8 @@
   "pad_token": null,
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
-  "suffix_first": false,
   "suffix_token": "▁<SUF>",
   "tokenizer_class": "CodeLlamaTokenizer",
-  "tokenizer_file": "/root/.cache/huggingface/hub/models--codellama--CodeLlama-13b-Instruct-hf/snapshots/ff0983bc4267bb98ead4fb5168fe2f049b442787/tokenizer.json",
-  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "use_fast": true
 }

 {
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
   "pad_token": null,
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
   "suffix_token": "▁<SUF>",
   "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }