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

Libraries

How to use GTKING/King_small with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-1B")
model = PeftModel.from_pretrained(base_model, "GTKING/King_small")

Transformers

How to use GTKING/King_small with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GTKING/King_small")
model = AutoModelForCausalLM.from_pretrained("GTKING/King_small")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GTKING/King_small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GTKING/King_small

SGLang

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

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

GTKING commited on 24 days ago

Commit

22585f3

verified ·

1 Parent(s): 29df41b

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

config.json +24 -22
generation_config.json +14 -0
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,30 +1,32 @@
 {
   "architectures": [
-    "ZFusionAIForCausalLM"
   ],
-  "hidden_size": 640,
   "initializer_range": 0.02,
-  "intermediate_size": 1856,
-  "kv_lora_rank": 96,
-  "max_position_embeddings": 65536,
-  "model_type": "zfusionai_v3",
-  "moe_aux_loss_coef": 0.01,
-  "num_attention_heads": 8,
-  "num_experts": 8,
-  "num_experts_per_tok": 2,
-  "num_hidden_layers": 16,
   "num_key_value_heads": 2,
-  "qk_rope_head_dim": 32,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "factor": 2.0,
-    "original_max_position_embeddings": 32768,
-    "type": "yarn"
   },
-  "rope_theta": 100000.0,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "use_cache": true,
-  "v_head_dim": 64,
-  "vocab_size": 50000
 }

 {
   "architectures": [
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
   "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 2,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
   },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.11.0",
+  "use_cache": false,
+  "vocab_size": 130560
 }

generation_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1,
+    130073
+  ],
+  "pad_token_id": 1,
+  "temperature": 0.9,
+  "top_p": 0.95,
+  "transformers_version": "5.11.0"
+}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10345edb6ccfb43485c1dab145e4922181e38d34545290d3feabe10b46e2a44b
-size 1006939264

 version https://git-lfs.github.com/spec/v1
+oid sha256:abd3d7e27d3e749331e49ed2780c327dbcab61fa9bdcce24ec9019c3eefc19bf
+size 2161290944