Instructions to use Niwet/qapyqlora80 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Niwet/qapyqlora80 with Transformers:

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

pipe = pipeline("text-generation", model="Niwet/qapyqlora80")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Niwet/qapyqlora80")
model = AutoModelForCausalLM.from_pretrained("Niwet/qapyqlora80")
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 Niwet/qapyqlora80 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Niwet/qapyqlora80"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Niwet/qapyqlora80",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Niwet/qapyqlora80

SGLang

How to use Niwet/qapyqlora80 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 "Niwet/qapyqlora80" \
    --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": "Niwet/qapyqlora80",
		"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 "Niwet/qapyqlora80" \
        --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": "Niwet/qapyqlora80",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Niwet/qapyqlora80 with Docker Model Runner:
```
docker model run hf.co/Niwet/qapyqlora80
```

Niwet commited on Apr 2, 2024

Commit

40c0daa

verified ·

1 Parent(s): e58a538

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

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

adapter_config.json CHANGED Viewed

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
     "o_proj",
-    "q_proj",
     "gate_proj",
-    "up_proj",
-    "v_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
+    "up_proj",
     "o_proj",
     "gate_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f4d1875354213311c2e8baf18c6db026cf7bc703ada839cb5dcb1e7afb1cd4
 size 39256456

 version https://git-lfs.github.com/spec/v1
+oid sha256:1966034f492f333aad34b5471c87a61396c16ba2c6d84fb56bbb9e95e0c6e31e
 size 39256456

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1069101ced2b939f6c65366ed794dbc006343a15de32cacf5012604304f95a53
 size 3212306456

 version https://git-lfs.github.com/spec/v1
+oid sha256:341b61df83912720b64c5cb75fc90613fd2a0775d74522266a74f341f262059e
 size 3212306456