Instructions to use darkps/darkit-v2.5-transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use darkps/darkit-v2.5-transformers with Transformers:

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

pipe = pipeline("text-generation", model="darkps/darkit-v2.5-transformers")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import darkit-v2.5
model = darkit-v2.5.from_pretrained("darkps/darkit-v2.5-transformers", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use darkps/darkit-v2.5-transformers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "darkps/darkit-v2.5-transformers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "darkps/darkit-v2.5-transformers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/darkps/darkit-v2.5-transformers

SGLang

How to use darkps/darkit-v2.5-transformers 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 "darkps/darkit-v2.5-transformers" \
    --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": "darkps/darkit-v2.5-transformers",
		"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 "darkps/darkit-v2.5-transformers" \
        --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": "darkps/darkit-v2.5-transformers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use darkps/darkit-v2.5-transformers with Docker Model Runner:
```
docker model run hf.co/darkps/darkit-v2.5-transformers
```

darkps commited on 4 days ago

Commit

dbd79e6

verified ·

1 Parent(s): 215e2ca

Upload notebook.ipynb

Browse files

Files changed (1) hide show

notebook.ipynb +99 -90

notebook.ipynb CHANGED Viewed

@@ -1,93 +1,102 @@
 {
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "!pip install llama-cpp-python huggingface_hub --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124\n"
-      ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from huggingface_hub import HfApi\n",
-        "from llama_cpp import Llama\n",
-        "import os\n",
-        "\n",
-        "REPO_ID = \"darkps/darkit-v2.5-transformers\"\n",
-        "api = HfApi()\n",
-        "\n",
-        "files = api.list_repo_files(REPO_ID)\n",
-        "gguf_files = [f for f in files if f.endswith(\".gguf\")]\n",
-        "\n",
-        "for i, f in enumerate(gguf_files):\n",
-        "    print(f\"[{i}] {f}\")\n",
-        "\n",
-        "choice = int(input(\"Select model number: \"))\n",
-        "filename = gguf_files[choice]\n",
-        "\n",
-        "llm = Llama.from_pretrained(\n",
-        "    repo_id=REPO_ID,\n",
-        "    filename=filename,\n",
-        "    n_ctx=2048,\n",
-        "    n_batch=128,\n",
-        "    n_ubatch=128,\n",
-        "    n_threads=os.cpu_count() or 4,\n",
-        "    n_threads_batch=os.cpu_count() or 4,\n",
-        "    n_gpu_layers=-1,\n",
-        "    verbose=False,\n",
-        "    no_perf=True,\n",
-        ")\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "llm.set_cache(None)\n",
-        "\n",
-        "PROMPT = \"Hi how are you?\"\n",
-        "\n",
-        "stream = llm(\n",
-        "    f\"<|im_start|>user\\n{PROMPT}<|im_end|>\\n<|im_start|>assistant\\n\",\n",
-        "    max_tokens=128,\n",
-        "    temperature=0.7,\n",
-        "    top_p=0.8,\n",
-        "    top_k=20,\n",
-        "    stream=True,\n",
-        "    stop=[\n",
-        "        \"<|im_end|>\",\n",
-        "        \"<|im_start|>\",\n",
-        "        \"\\n\\nUser:\",\n",
-        "        \"\\n\\nAssistant:\"\n",
-        "    ],\n",
-        "    echo=False\n",
-        ")\n",
-        "\n",
-        "for chunk in stream:\n",
-        "    text = chunk[\"choices\"][0][\"text\"]\n",
-        "\n",
-        "    if text:\n",
-        "        print(text, end=\"\", flush=True)\n",
-        "\n",
-        "print()\n"
-      ]
-    }
-  ],
-  "metadata": {
-    "kernelspec": {
-      "display_name": "Python 3",
-      "language": "python",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
 }

 {
+    "cells": [
+        {
+            "cell_type": "code",
+            "execution_count": None,
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "!pip install -U transformers accelerate huggingface_hub sentencepiece safetensors\n"
+            ],
+        },
+        {
+            "cell_type": "code",
+            "execution_count": None,
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "from huggingface_hub import HfApi\n",
+                "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+                "import torch\n",
+                "import os\n",
+                "\n",
+                "REPO_ID = \"darkps/darkit-v2.5-transformers\"\n",
+                "api = HfApi()\n",
+                "\n",
+                "files = api.list_repo_files(REPO_ID)\n",
+                "model_files = [f for f in files if f.endswith(\".safetensors\") or f.endswith(\".bin\")]\n",
+                "\n",
+                "for i, f in enumerate(model_files):\n",
+                "    print(f\"[{i}] {f}\")\n",
+                "\n",
+                "tokenizer = AutoTokenizer.from_pretrained(REPO_ID, trust_remote_code=True)\n",
+                "\n",
+                "model = AutoModelForCausalLM.from_pretrained(\n",
+                "    REPO_ID,\n",
+                "    trust_remote_code=True,\n",
+                "    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,\n",
+                "    device_map=\"auto\",\n",
+                "    low_cpu_mem_usage=True,\n",
+                ")\n",
+            ],
+        },
+        {
+            "cell_type": "code",
+            "execution_count": None,
+            "metadata": {},
+            "outputs": [],
+            "source": [
+                "from transformers import TextIteratorStreamer\n",
+                "from threading import Thread\n",
+                "\n",
+                "PROMPT = \"Hi how are you?\"\n",
+                "\n",
+                "messages = [\n",
+                "    {\"role\": \"user\", \"content\": PROMPT}\n",
+                "]\n",
+                "\n",
+                "inputs = tokenizer.apply_chat_template(\n",
+                "    messages,\n",
+                "    tokenize=True,\n",
+                "    add_generation_prompt=True,\n",
+                "    return_tensors=\"pt\"\n",
+                ")\n",
+                "\n",
+                "inputs = inputs.to(model.device)\n",
+                "\n",
+                "streamer = TextIteratorStreamer(\n",
+                "    tokenizer,\n",
+                "    skip_prompt=True,\n",
+                "    skip_special_tokens=True\n",
+                ")\n",
+                "\n",
+                "gen_kwargs = dict(\n",
+                "    inputs,\n",
+                "    max_new_tokens=128,\n",
+                "    temperature=0.7,\n",
+                "    top_p=0.8,\n",
+                "    top_k=20,\n",
+                "    do_sample=True,\n",
+                "    streamer=streamer,\n",
+                ")\n",
+                "\n",
+                "thread = Thread(target=model.generate, kwargs=gen_kwargs)\n",
+                "thread.start()\n",
+                "\n",
+                "for text in streamer:\n",
+                "    print(text, end=\"\", flush=True)\n",
+                "\n",
+                "print()\n",
+            ],
+        },
+    ],
+    "metadata": {
+        "kernelspec": {
+            "display_name": "Python 3",
+            "language": "python",
+            "name": "python3",
+        }
     },
+    "nbformat": 4,
+    "nbformat_minor": 0,
 }