Instructions to use WillHeld/debug_llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WillHeld/debug_llama with Transformers:

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

pipe = pipeline("text-generation", model="WillHeld/debug_llama")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WillHeld/debug_llama")
model = AutoModelForCausalLM.from_pretrained("WillHeld/debug_llama")
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 WillHeld/debug_llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/WillHeld/debug_llama

SGLang

How to use WillHeld/debug_llama 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 "WillHeld/debug_llama" \
    --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": "WillHeld/debug_llama",
		"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 "WillHeld/debug_llama" \
        --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": "WillHeld/debug_llama",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WillHeld/debug_llama with Docker Model Runner:
```
docker model run hf.co/WillHeld/debug_llama
```

WillHeld commited on Mar 19, 2024

Commit

d12a310

verified ·

1 Parent(s): 2607987

Upload LlamaForCausalLM

Browse files

Files changed (2) hide show

config.json +5 -5
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -7,14 +7,14 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 16,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 2048,
   "model_type": "llama",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 4,
-  "num_key_value_heads": 4,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -23,5 +23,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
-  "vocab_size": 10000
 }

   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
+  "hidden_size": 4,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 2048,
   "model_type": "llama",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_cache": true,
+  "vocab_size": 1000
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52abc8a1ba2707f2f8cc9c1641d59c296b4a936ed14ed79136e071b263b179f4
-size 9755216

 version https://git-lfs.github.com/spec/v1
+oid sha256:39f94c2be98e85dc96782ac6832fb156ce8c9ae5cdeff70821ec101a136de473
+size 1091504