Instructions to use patched-codes/patched-coder-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patched-codes/patched-coder-34b with Transformers:

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

pipe = pipeline("text-generation", model="patched-codes/patched-coder-34b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("patched-codes/patched-coder-34b")
model = AutoModelForCausalLM.from_pretrained("patched-codes/patched-coder-34b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use patched-codes/patched-coder-34b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/patched-codes/patched-coder-34b

SGLang

How to use patched-codes/patched-coder-34b 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 "patched-codes/patched-coder-34b" \
    --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": "patched-codes/patched-coder-34b",
		"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 "patched-codes/patched-coder-34b" \
        --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": "patched-codes/patched-coder-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use patched-codes/patched-coder-34b with Docker Model Runner:
```
docker model run hf.co/patched-codes/patched-coder-34b
```

codelion commited on Nov 16, 2023

Commit

4082ea6

1 Parent(s): 914b382

Upload tokenizer

Browse files

Files changed (2) hide show

special_tokens_map.json +25 -3
tokenizer_config.json +7 -1

special_tokens_map.json CHANGED Viewed

@@ -11,9 +11,31 @@
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
     "▁<EOT>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "unk_token": "<unk>"
 }

     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
     "▁<EOT>"
   ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json CHANGED Viewed

@@ -1,4 +1,6 @@
 {
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -69,6 +71,10 @@
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
     "▁<EOT>"
   ],
   "bos_token": "<s>",
@@ -76,7 +82,7 @@
   "eos_token": "</s>",
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",
-  "legacy": null,
   "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,

 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
     "▁<EOT>"
   ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",
+  "legacy": false,
   "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,