Instructions to use hopski/graph-qwenputer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hopski/graph-qwenputer with Transformers:

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

pipe = pipeline("text-generation", model="hopski/graph-qwenputer")
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("hopski/graph-qwenputer")
model = AutoModelForCausalLM.from_pretrained("hopski/graph-qwenputer", 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 hopski/graph-qwenputer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hopski/graph-qwenputer

SGLang

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

Docker Model Runner
How to use hopski/graph-qwenputer with Docker Model Runner:
```
docker model run hf.co/hopski/graph-qwenputer
```

graph-qwenputer / chipformer.json

hopski

Add files using upload-large-folder tool

1bfff65 verified 6 days ago

Raw History Blame Contribute Delete

2.37 kB

{
 "layout": "rv1-tok",
 "chip_token_offset": 248320,
 "chip_vocab": 236469,
 "chip_layers": 11,
 "qwen_layers_from": 11,
 "hidden": 3968,
 "chip_dims_offset": 2560,
 "ballast_dims": 62,
 "circuit": {
  "layers": 11,
  "dims": 2919,
  "heads": 103,
  "ffn_units": 42199,
  "max_units": 8149,
  "max_heads": 16
 },
 "slots": 1266,
 "muted": true,
 "code_dims": [
  2754,
  2755,
  2756,
  2757,
  2758,
  2759,
  2760,
  2761,
  2762,
  2763,
  2764,
  2765,
  2766,
  2767,
  2768,
  2769,
  2770,
  2771,
  2772,
  2773,
  2774
 ],
 "tau_dim": 2777,
 "mu_dim": 2776,
 "nfam": 5,
 "npay": 16,
 "tool_call": [
  248058,
  248059
 ],
 "printable": [
  188,
  189,
  190,
  191,
  192,
  193,
  194,
  195,
  196,
  197,
  198,
  199,
  200,
  201,
  202,
  203,
  204,
  205,
  206,
  207,
  208,
  209,
  210,
  211,
  212,
  213,
  214,
  215,
  216,
  217,
  218,
  219,
  220,
  0,
  1,
  2,
  3,
  4,
  5,
  6,
  7,
  8,
  9,
  10,
  11,
  12,
  13,
  14,
  15,
  16,
  17,
  18,
  19,
  20,
  21,
  22,
  23,
  24,
  25,
  26,
  27,
  28,
  29,
  30,
  31,
  32,
  33,
  34,
  35,
  36,
  37,
  38,
  39,
  40,
  41,
  42,
  43,
  44,
  45,
  46,
  47,
  48,
  49,
  50,
  51,
  52,
  53,
  54,
  55,
  56,
  57,
  58,
  59,
  60,
  61,
  62,
  63,
  64,
  65,
  66,
  67,
  68,
  69,
  70,
  71,
  72,
  73,
  74,
  75,
  76,
  77,
  78,
  79,
  80,
  81,
  82,
  83,
  84,
  85,
  86,
  87,
  88,
  89,
  90,
  91,
  92,
  93,
  221,
  222,
  223,
  224,
  225,
  226,
  227,
  228,
  229,
  230,
  231,
  232,
  233,
  234,
  235,
  236,
  237,
  238,
  239,
  240,
  241,
  242,
  243,
  244,
  245,
  246,
  247,
  248,
  249,
  250,
  251,
  252,
  253,
  254,
  94,
  95,
  96,
  97,
  98,
  99,
  100,
  101,
  102,
  103,
  104,
  105,
  255,
  106,
  107,
  108,
  109,
  110,
  111,
  112,
  113,
  114,
  115,
  116,
  117,
  118,
  119,
  120,
  121,
  122,
  123,
  124,
  125,
  126,
  127,
  128,
  129,
  130,
  131,
  132,
  133,
  134,
  135,
  136,
  137,
  138,
  139,
  140,
  141,
  142,
  143,
  144,
  145,
  146,
  147,
  148,
  149,
  150,
  151,
  152,
  153,
  154,
  155,
  156,
  157,
  158,
  159,
  160,
  161,
  162,
  163,
  164,
  165,
  166,
  167,
  168,
  169,
  170,
  171,
  172,
  173,
  174,
  175,
  176,
  177,
  178,
  179,
  180,
  181,
  182,
  183,
  184,
  185,
  186,
  187,
  248066,
  248067,
  248068,
  248069
 ]
}

	{
	"layout": "rv1-tok",
	"chip_token_offset": 248320,
	"chip_vocab": 236469,
	"chip_layers": 11,
	"qwen_layers_from": 11,
	"hidden": 3968,
	"chip_dims_offset": 2560,
	"ballast_dims": 62,
	"circuit": {
	"layers": 11,
	"dims": 2919,
	"heads": 103,
	"ffn_units": 42199,
	"max_units": 8149,
	"max_heads": 16
	},
	"slots": 1266,
	"muted": true,
	"code_dims": [
	2754,
	2755,
	2756,
	2757,
	2758,
	2759,
	2760,
	2761,
	2762,
	2763,
	2764,
	2765,
	2766,
	2767,
	2768,
	2769,
	2770,
	2771,
	2772,
	2773,
	2774
	],
	"tau_dim": 2777,
	"mu_dim": 2776,
	"nfam": 5,
	"npay": 16,
	"tool_call": [
	248058,
	248059
	],
	"printable": [
	188,
	189,
	190,
	191,
	192,
	193,
	194,
	195,
	196,
	197,
	198,
	199,
	200,
	201,
	202,
	203,
	204,
	205,
	206,
	207,
	208,
	209,
	210,
	211,
	212,
	213,
	214,
	215,
	216,
	217,
	218,
	219,
	220,
	0,
	1,
	2,
	3,
	4,
	5,
	6,
	7,
	8,
	9,
	10,
	11,
	12,
	13,
	14,
	15,
	16,
	17,
	18,
	19,
	20,
	21,
	22,
	23,
	24,
	25,
	26,
	27,
	28,
	29,
	30,
	31,
	32,
	33,
	34,
	35,
	36,
	37,
	38,
	39,
	40,
	41,
	42,
	43,
	44,
	45,
	46,
	47,
	48,
	49,
	50,
	51,
	52,
	53,
	54,
	55,
	56,
	57,
	58,
	59,
	60,
	61,
	62,
	63,
	64,
	65,
	66,
	67,
	68,
	69,
	70,
	71,
	72,
	73,
	74,
	75,
	76,
	77,
	78,
	79,
	80,
	81,
	82,
	83,
	84,
	85,
	86,
	87,
	88,
	89,
	90,
	91,
	92,
	93,
	221,
	222,
	223,
	224,
	225,
	226,
	227,
	228,
	229,
	230,
	231,
	232,
	233,
	234,
	235,
	236,
	237,
	238,
	239,
	240,
	241,
	242,
	243,
	244,
	245,
	246,
	247,
	248,
	249,
	250,
	251,
	252,
	253,
	254,
	94,
	95,
	96,
	97,
	98,
	99,
	100,
	101,
	102,
	103,
	104,
	105,
	255,
	106,
	107,
	108,
	109,
	110,
	111,
	112,
	113,
	114,
	115,
	116,
	117,
	118,
	119,
	120,
	121,
	122,
	123,
	124,
	125,
	126,
	127,
	128,
	129,
	130,
	131,
	132,
	133,
	134,
	135,
	136,
	137,
	138,
	139,
	140,
	141,
	142,
	143,
	144,
	145,
	146,
	147,
	148,
	149,
	150,
	151,
	152,
	153,
	154,
	155,
	156,
	157,
	158,
	159,
	160,
	161,
	162,
	163,
	164,
	165,
	166,
	167,
	168,
	169,
	170,
	171,
	172,
	173,
	174,
	175,
	176,
	177,
	178,
	179,
	180,
	181,
	182,
	183,
	184,
	185,
	186,
	187,
	248066,
	248067,
	248068,
	248069
	]
	}