Instructions to use inaciose/inacio-sft-d16v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inaciose/inacio-sft-d16v1 with Transformers:

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

pipe = pipeline("text-generation", model="inaciose/inacio-sft-d16v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("inaciose/inacio-sft-d16v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inaciose/inacio-sft-d16v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inaciose/inacio-sft-d16v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inaciose/inacio-sft-d16v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inaciose/inacio-sft-d16v1

SGLang

How to use inaciose/inacio-sft-d16v1 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 "inaciose/inacio-sft-d16v1" \
    --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": "inaciose/inacio-sft-d16v1",
		"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 "inaciose/inacio-sft-d16v1" \
        --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": "inaciose/inacio-sft-d16v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inaciose/inacio-sft-d16v1 with Docker Model Runner:
```
docker model run hf.co/inaciose/inacio-sft-d16v1
```

inaciose commited on 3 days ago

Commit

7ba5765

verified ·

1 Parent(s): 6c49891

Upload de d16

Browse files

Files changed (6) hide show

meta_000699.json +38 -0
model_000699.pt +3 -0
optim_000699_rank0.pt +3 -0
optim_000699_rank1.pt +3 -0
optim_000699_rank2.pt +3 -0
optim_000699_rank3.pt +3 -0

meta_000699.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "step": 699,
+  "val_bpb": 0.15301302843251394,
+  "model_config": {
+    "sequence_len": 2048,
+    "vocab_size": 65536,
+    "n_layer": 16,
+    "n_head": 8,
+    "n_kv_head": 8,
+    "n_embd": 1024,
+    "window_pattern": "SSSL"
+  },
+  "user_config": {
+    "run": "nanochatpt-d16-full",
+    "device_type": "",
+    "model_tag": null,
+    "model_step": null,
+    "load_optimizer": 1,
+    "num_iterations": -1,
+    "max_seq_len": null,
+    "device_batch_size": 4,
+    "total_batch_size": null,
+    "embedding_lr": null,
+    "unembedding_lr": null,
+    "matrix_lr": null,
+    "init_lr_frac": 0.8,
+    "warmup_ratio": 0.0,
+    "warmdown_ratio": 0.5,
+    "final_lr_frac": 0.0,
+    "eval_every": 200,
+    "eval_tokens": 20971520,
+    "chatcore_every": 200,
+    "chatcore_max_cat": -1,
+    "chatcore_max_sample": 24,
+    "mmlu_epochs": 3,
+    "gsm8k_epochs": 4
+  }
+}

model_000699.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:de2e19599a24daa1a5499b2bcc95d5247099f1f136d0f3fe01a46a968b7cda29
+size 2281752258

optim_000699_rank0.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c141a24a54200c4f7b445b18885b3c01fd35a324bc26f4faabfbce9c47373f95
+size 939735701

optim_000699_rank1.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2257490b31bc73498d867daac9057baeb238171a89d0e14302806cd23077be
+size 939735701

optim_000699_rank2.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2a290ed5f8c138a3f005a65c6311962eeb52014b7c5f8959be3dadd11b95e028
+size 939735701

optim_000699_rank3.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:30aeccbe91f4b75ab11b08e46e32d9ea552b6fb181ea456c00f94658c54f6aca
+size 939735701