Instructions to use FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python with Transformers:

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

pipe = pipeline("text-generation", model="FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python")
model = AutoModelForCausalLM.from_pretrained("FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python")
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 FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python

SGLang

How to use FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python 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 "FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python" \
    --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": "FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python",
		"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 "FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python" \
        --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": "FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python",
    max_seq_length=2048,
)

Docker Model Runner
How to use FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python with Docker Model Runner:
```
docker model run hf.co/FYPFAST/Llama-3.2-3B-Instruct-PEP8-Vulnerability-Python
```

omaisafzal commited on Jan 19, 2025

Commit

ec56ad2

verified ·

1 Parent(s): 4a419e6

Training in progress, step 60

Browse files

Files changed (7) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
runs/Jan19_14-47-45_78825b1c884c/events.out.tfevents.1737298069.78825b1c884c.842.0 +3 -0
runs/Jan19_14-54-34_78825b1c884c/events.out.tfevents.1737298478.78825b1c884c.3171.0 +3 -0
runs/Jan19_14-59-49_78825b1c884c/events.out.tfevents.1737298799.78825b1c884c.4514.0 +3 -0
tokenizer_config.json +2 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -26,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj",
     "up_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "down_proj",
+    "k_proj",
     "up_proj",
+    "v_proj",
+    "o_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:d3eaa6802a6cf426a401cce4cb18677984a228c4b4b59d8a8df7d97429d608d2
 size 1965084424

 version https://git-lfs.github.com/spec/v1
+oid sha256:93736007f12a3974f70ff4cf5b753f8d405da0607b55a58e5b10e99ea5275768
 size 1965084424

runs/Jan19_14-47-45_78825b1c884c/events.out.tfevents.1737298069.78825b1c884c.842.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ecbe3077dc1f09dc5b811f7b495a71bfb58ea91fbf3f767b0d758de6ae710d
+size 6758

runs/Jan19_14-54-34_78825b1c884c/events.out.tfevents.1737298478.78825b1c884c.3171.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:caea4d6d070365d6dfc182c33640b5a75cc5ae15b873a5077b1f4153c65e5213
+size 4184

runs/Jan19_14-59-49_78825b1c884c/events.out.tfevents.1737298799.78825b1c884c.4514.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f5cc4d233db3209c9e7b8bfc8610262ae7fbb5f9184b94310985898c27b8d4da
+size 18905

tokenizer_config.json CHANGED Viewed

@@ -2061,5 +2061,6 @@
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizerFast"
 }

   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
 }

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539ee36d033b56b7bc95db41e3ca1b482704c3f01d26d3552ad5f5872996baa1
 size 5688

 version https://git-lfs.github.com/spec/v1
+oid sha256:5dc72f1a806648eddd48aaaf229f3f4b2ee9b82862e95cf253bf915c14567fc1
 size 5688