Instructions to use loginworks/Meta-Llama-3-8B-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use loginworks/Meta-Llama-3-8B-code with Transformers:

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

pipe = pipeline("text-generation", model="loginworks/Meta-Llama-3-8B-code")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("loginworks/Meta-Llama-3-8B-code")
model = AutoModelForCausalLM.from_pretrained("loginworks/Meta-Llama-3-8B-code")
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 loginworks/Meta-Llama-3-8B-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "loginworks/Meta-Llama-3-8B-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "loginworks/Meta-Llama-3-8B-code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/loginworks/Meta-Llama-3-8B-code

SGLang

How to use loginworks/Meta-Llama-3-8B-code 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 "loginworks/Meta-Llama-3-8B-code" \
    --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": "loginworks/Meta-Llama-3-8B-code",
		"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 "loginworks/Meta-Llama-3-8B-code" \
        --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": "loginworks/Meta-Llama-3-8B-code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use loginworks/Meta-Llama-3-8B-code with Docker Model Runner:
```
docker model run hf.co/loginworks/Meta-Llama-3-8B-code
```

filipemiguelmartins commited on Jul 3, 2024

Commit

e2ea3a9

verified ·

1 Parent(s): 03d793f

Upload LlamaForCausalLM

Browse files

Files changed (6) hide show

config.json +1 -1
model-00001-of-00004.safetensors +2 -2
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +2 -2
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -25,5 +25,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 128264
 }

   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": true,
+  "vocab_size": 128256
 }

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a795fedb82ce808b73a52b73a0e1acc02b04178f0c763a6b3c8cfaa4886010
-size 4976764208

 version https://git-lfs.github.com/spec/v1
+oid sha256:e8f0a69fe78730bb9f8e75ebe279d450e268c43276874e27489843e47398bd06
+size 4976698672

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c296b1024f077c3a4b558a3d57cc7c3bf8a8d7148999eeefe11eaf8f58ce6afc
 size 4999802720

 version https://git-lfs.github.com/spec/v1
+oid sha256:d49f6aad8b177e06ffa21c448288e66aada69afcefd85cde1fa3c3f98b2ed4c2
 size 4999802720

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86adbb59d605076458a1f05ed3c23298c6585da8bb10f4e6aaaa9820def88258
 size 4915916176

 version https://git-lfs.github.com/spec/v1
+oid sha256:6e58079b5e019b747713ab713fec01124b85bf5e4b351890e94f88d305057fe7
 size 4915916176

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc296a5aafdecf3a1e1414c2590a247fe8aa733d01cafe6995cd818b0ca05ec
-size 1168204344

 version https://git-lfs.github.com/spec/v1
+oid sha256:1844a5727bcea3f8f12c7ce9cfd799ce4a583a9dcc949d91a6295f52d0647563
+size 1168138808

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16060653568
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",

 {
   "metadata": {
+    "total_size": 16060522496
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",