Instructions to use eekay/gpt-no-hack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eekay/gpt-no-hack with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gpt-oss-120b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "eekay/gpt-no-hack")

Transformers

How to use eekay/gpt-no-hack with Transformers:

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

pipe = pipeline("text-generation", model="eekay/gpt-no-hack")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("eekay/gpt-no-hack", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eekay/gpt-no-hack with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eekay/gpt-no-hack"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eekay/gpt-no-hack",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eekay/gpt-no-hack

SGLang

How to use eekay/gpt-no-hack 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 "eekay/gpt-no-hack" \
    --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": "eekay/gpt-no-hack",
		"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 "eekay/gpt-no-hack" \
        --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": "eekay/gpt-no-hack",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use eekay/gpt-no-hack with Docker Model Runner:
```
docker model run hf.co/eekay/gpt-no-hack
```

eekay commited on Mar 1

Commit

cd482f2

verified ·

1 Parent(s): 91bc592

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "gate_proj",
     "up_proj",
-    "q_proj",
     "v_proj",
-    "down_proj"
   ],
   "target_parameters": [
     "mlp.experts.gate_up_proj",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "o_proj",
     "up_proj",
     "v_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
   ],
   "target_parameters": [
     "mlp.experts.gate_up_proj",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73262356201c3ceea5472d29181d437a7ca527446a46984bf784cfd5ed12d51a
 size 95590192

 version https://git-lfs.github.com/spec/v1
+oid sha256:3878bdb1b5180718537b66104943dd661e1808767ac489740de852da7d130fa8
 size 95590192