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

Libraries

How to use isabelagregio/reduced_model with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("isabelagregio/reduced_model")
model = AutoModelForCausalLM.from_pretrained("isabelagregio/reduced_model", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use isabelagregio/reduced_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/isabelagregio/reduced_model

SGLang

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

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

isabelagregio commited on Oct 23, 2024

Commit

c02c842

verified ·

1 Parent(s): 39ac5bc

Salvando modelo reduzido

Browse files

Files changed (3) hide show

config.json +1 -1
model-00003-of-00003.safetensors +2 -2
model.safetensors.index.json +1 -10

config.json CHANGED Viewed

@@ -16,7 +16,7 @@
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 26,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
+  "num_hidden_layers": 25,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd6048a6d74aa619f7aec9c38761f3bad30ba7a58b961dcd8e8ed0632449a4e
-size 1161882168

 version https://git-lfs.github.com/spec/v1
+oid sha256:b4c3c6dd2dd3cb7505ddc9ac9e3b72d4f31ceacb9021653b11783a9bb23ff7a8
+size 757114408

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 11048230912
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -167,15 +167,6 @@
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",

 {
   "metadata": {
+    "total_size": 10643464192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",