Instructions to use RayMelius/stockex-ch-trader with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RayMelius/stockex-ch-trader with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "RayMelius/stockex-ch-trader")

Transformers

How to use RayMelius/stockex-ch-trader with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RayMelius/stockex-ch-trader")
model = AutoModelForCausalLM.from_pretrained("RayMelius/stockex-ch-trader", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RayMelius/stockex-ch-trader with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RayMelius/stockex-ch-trader

SGLang

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

Docker Model Runner
How to use RayMelius/stockex-ch-trader with Docker Model Runner:
```
docker model run hf.co/RayMelius/stockex-ch-trader
```

RayMelius commited on Mar 6

Commit

ece68cd

verified ·

1 Parent(s): 3c07c79

StockEx CH Trader: QLoRA fine-tuned Qwen/Qwen2.5-7B-Instruct (adapter)

Browse files

Files changed (1) hide show

adapter_config.json +4 -4

adapter_config.json CHANGED Viewed

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

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