Instructions to use blackdaqlabs/MiloX1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blackdaqlabs/MiloX1 with Transformers:

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

pipe = pipeline("text-generation", model="blackdaqlabs/MiloX1")
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("blackdaqlabs/MiloX1")
model = AutoModelForCausalLM.from_pretrained("blackdaqlabs/MiloX1", 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 blackdaqlabs/MiloX1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blackdaqlabs/MiloX1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blackdaqlabs/MiloX1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blackdaqlabs/MiloX1

SGLang

How to use blackdaqlabs/MiloX1 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 "blackdaqlabs/MiloX1" \
    --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": "blackdaqlabs/MiloX1",
		"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 "blackdaqlabs/MiloX1" \
        --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": "blackdaqlabs/MiloX1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use blackdaqlabs/MiloX1 with Docker Model Runner:
```
docker model run hf.co/blackdaqlabs/MiloX1
```

teszenofficial commited on 22 days ago

Commit

3ebd018

verified ·

1 Parent(s): 0b3add2

Upload 5 files

Browse files

Files changed (4) hide show

README.md +3 -0
config.json +37 -0
model.safetensors +3 -0
tokenizer.json +0 -0

README.md ADDED Viewed

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


1	+ # Milo X1 (dpo)
2	+
3	+ Transformer en español entrenado desde cero. ~12.3M parámetros, GQA + RoPE + QK-Norm + SwiGLU + RMSNorm. Cargar con `milo_core.load_model`. Plantilla de chat con tokens especiales (`<\|user\|>`, `<\|assistant\|>`, `<\|end\|>`).

config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "vocab_size": 16384,
+  "d_model": 320,
+  "n_layers": 6,
+  "n_heads": 5,
+  "n_kv_heads": 1,
+  "d_ff": 960,
+  "context_length": 768,
+  "dropout": 0.0,
+  "rope_theta": 100000.0,
+  "qk_norm": true,
+  "logit_softcap": 30.0,
+  "z_loss": 0.0001,
+  "tie_embeddings": true,
+  "architecture": "MiloX1",
+  "stage": "dpo",
+  "special_tokens": [
+    "<PAD>",
+    "<UNK>",
+    "<BOS>",
+    "<EOS>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|end|>",
+    "<|reserved_0|>",
+    "<|reserved_1|>",
+    "<|reserved_2|>",
+    "<|reserved_3|>",
+    "<|reserved_4|>",
+    "<|reserved_5|>",
+    "<|reserved_6|>",
+    "<|reserved_7|>"
+  ],
+  "chat_template": "<BOS>[<|system|>S<|end|>]<|user|>U<|end|><|assistant|>A<|end|>",
+  "core_version": "4.0"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a8585dbbc84fd5c63910330f9990240707f529a39dd5e87cc55703e68a72ed
+size 49013720

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff