Instructions to use haihp02/rrr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haihp02/rrr with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "haihp02/rrr")

Transformers

How to use haihp02/rrr with Transformers:

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

pipe = pipeline("text-generation", model="haihp02/rrr")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("haihp02/rrr", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use haihp02/rrr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haihp02/rrr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haihp02/rrr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/haihp02/rrr

SGLang

How to use haihp02/rrr 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 "haihp02/rrr" \
    --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": "haihp02/rrr",
		"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 "haihp02/rrr" \
        --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": "haihp02/rrr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use haihp02/rrr with Docker Model Runner:
```
docker model run hf.co/haihp02/rrr
```

haihp02 commited on 16 days ago

Commit

f43fece

verified ·

1 Parent(s): 9e82c0a

Upload checkpoint

Browse files

Files changed (3) hide show

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

adapter_config.json CHANGED Viewed

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
     "q_proj",
-    "o_proj",
-    "gate_proj",
     "down_proj",
-    "v_proj",
-    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

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

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec0cf448f4e511ec46de10331d69933dad8d00b28bba111e06a19a271d7be61
 size 239536272

 version https://git-lfs.github.com/spec/v1
+oid sha256:2a3402ccc1fc7a922b5e964b2e95b2f3b2c20ec3e100b567b0065d7f01ece3b0
 size 239536272

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872dc618d9eb67bfd3278bd2dfc2a33f9a3295703e14fde998763d34ce1a44a1
 size 6353

 version https://git-lfs.github.com/spec/v1
+oid sha256:80048129f36e2358aff73fcb7cc5eb59e43a169f944ff161a047c3714f1f7c4f
 size 6353