Instructions to use my-ai-stack/Stack-2-9-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use my-ai-stack/Stack-2-9-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="my-ai-stack/Stack-2-9-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned")
model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-2-9-finetuned")
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

vLLM

How to use my-ai-stack/Stack-2-9-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "my-ai-stack/Stack-2-9-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "my-ai-stack/Stack-2-9-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/my-ai-stack/Stack-2-9-finetuned

SGLang

How to use my-ai-stack/Stack-2-9-finetuned 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 "my-ai-stack/Stack-2-9-finetuned" \
    --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": "my-ai-stack/Stack-2-9-finetuned",
		"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 "my-ai-stack/Stack-2-9-finetuned" \
        --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": "my-ai-stack/Stack-2-9-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use my-ai-stack/Stack-2-9-finetuned with Docker Model Runner:
```
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
```

walidsobhie-code commited on Apr 4

Commit

24de6c8

1 Parent(s): 6a2254e

fix: add train_dir and eval_dir to config for Kaggle

Browse files

Files changed (1) hide show

stack/training/train_config_local.yaml +19 -30

stack/training/train_config_local.yaml CHANGED Viewed

@@ -1,39 +1,33 @@
-# Stack 2.9 Training Configuration - Local/MPS Optimized
-# Model Configuration
 model:
-  name: "./base_model_qwen7b"
   trust_remote_code: true
-  torch_dtype: "float16"
-# Data Configuration
 data:
-  input_path: "./data/final/train_with_rtmp.jsonl"
   train_dir: null
   eval_dir: null
   max_length: 2048
   train_split: 0.9
   test_split: 0.1
-# LoRA Configuration
 lora:
   r: 16
   alpha: 32
   dropout: 0.05
   target_modules:
-    - "q_proj"
-    - "k_proj"
-    - "v_proj"
-    - "o_proj"
-  bias: "none"
-  task_type: "CAUSAL_LM"
-# Training Configuration
 training:
   num_epochs: 1
-  batch_size: 1
   gradient_accumulation: 4
-  learning_rate: 2.0e-4
   warmup_steps: 50
   weight_decay: 0.01
   max_grad_norm: 1.0
@@ -45,27 +39,22 @@ training:
   bf16: false
   gradient_checkpointing: true
-# Output Configuration
 output:
-  lora_dir: "./training_output/lora"
-  merged_dir: "./training_output/merged"
-  awq_dir: "./training_output/awq"
-# Quantization Configuration
 quantization:
   enabled: false
   bits: 4
   group_size: 128
-# Logging Configuration
 logging:
-  report_to: "none"
-  wandb_project: "stack-2.9-training"
-  run_name: null
-# Hardware Configuration
 hardware:
-  device: "mps"
-  num_gpus: 0
   use_4bit: false
-  use_8bit: false

 model:
+  name: /kaggle/working/stack-2.9/base_model_qwen7b
   trust_remote_code: true
+  torch_dtype: float16
 data:
+  input_path: /kaggle/working/stack-2.9/data/final/train.jsonl
   train_dir: null
   eval_dir: null
   max_length: 2048
   train_split: 0.9
   test_split: 0.1
 lora:
   r: 16
   alpha: 32
   dropout: 0.05
   target_modules:
+    - q_proj
+    - k_proj
+    - v_proj
+    - o_proj
+  bias: none
+  task_type: CAUSAL_LM
 training:
   num_epochs: 1
+  batch_size: 2
   gradient_accumulation: 4
+  learning_rate: 0.0002
   warmup_steps: 50
   weight_decay: 0.01
   max_grad_norm: 1.0
   bf16: false
   gradient_checkpointing: true
 output:
+  lora_dir: /kaggle/working/stack-2.9/training_output/lora
+  merged_dir: /kaggle/working/stack-2.9/training_output/merged
+  awq_dir: /kaggle/working/stack-2.9/training_output/awq
 quantization:
   enabled: false
   bits: 4
   group_size: 128
 logging:
+  report_to: none
+  wandb_project: stack-2.9-training
 hardware:
+  device: cuda
+  num_gpus: 1
   use_4bit: false
+  use_8bit: false