Instructions to use Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15 with Transformers:

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

pipe = pipeline("text-generation", model="Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15")
model = AutoModelForCausalLM.from_pretrained("Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15

SGLang

How to use Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15 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 "Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15" \
    --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": "Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15",
		"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 "Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15" \
        --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": "Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15 with Docker Model Runner:
```
docker model run hf.co/Devy1/CodeLlama-7b-hf-AQLM-8bit-code-4x15
```

Devy1 commited on Jan 26, 2025

Commit

dde3acc

verified ·

1 Parent(s): a8f21f8

Upload tokenizer

Browse files

Files changed (4) hide show

special_tokens_map.json +4 -0
tokenizer.json +1 -0
tokenizer.model +3 -0
tokenizer_config.json +5 -0

special_tokens_map.json CHANGED Viewed

@@ -1,5 +1,9 @@
 {
   "additional_special_tokens": [
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",

 {
   "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",

tokenizer.json CHANGED Viewed

@@ -170,6 +170,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json CHANGED Viewed

@@ -60,6 +60,10 @@
     }
   },
   "additional_special_tokens": [
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
@@ -67,6 +71,7 @@
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",

     }
   },
   "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
     "▁<PRE>",
     "▁<MID>",
     "▁<SUF>",
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
+  "device_map": "auto",
   "eos_token": "</s>",
   "eot_token": "▁<EOT>",
   "fill_token": "<FILL_ME>",