Instructions to use rayenmalouche/LLAMA3_3BfullData with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rayenmalouche/LLAMA3_3BfullData with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "rayenmalouche/LLAMA3_3BfullData")

Transformers

How to use rayenmalouche/LLAMA3_3BfullData with Transformers:

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

pipe = pipeline("text-generation", model="rayenmalouche/LLAMA3_3BfullData")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rayenmalouche/LLAMA3_3BfullData")
model = AutoModelForCausalLM.from_pretrained("rayenmalouche/LLAMA3_3BfullData", 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 rayenmalouche/LLAMA3_3BfullData with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rayenmalouche/LLAMA3_3BfullData"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rayenmalouche/LLAMA3_3BfullData",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rayenmalouche/LLAMA3_3BfullData

SGLang

How to use rayenmalouche/LLAMA3_3BfullData 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 "rayenmalouche/LLAMA3_3BfullData" \
    --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": "rayenmalouche/LLAMA3_3BfullData",
		"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 "rayenmalouche/LLAMA3_3BfullData" \
        --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": "rayenmalouche/LLAMA3_3BfullData",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use rayenmalouche/LLAMA3_3BfullData 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 rayenmalouche/LLAMA3_3BfullData 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 rayenmalouche/LLAMA3_3BfullData to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rayenmalouche/LLAMA3_3BfullData to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="rayenmalouche/LLAMA3_3BfullData",
    max_seq_length=2048,
)

Docker Model Runner
How to use rayenmalouche/LLAMA3_3BfullData with Docker Model Runner:
```
docker model run hf.co/rayenmalouche/LLAMA3_3BfullData
```

rayenmalouche commited on Oct 16, 2025

Commit

9d4a5b6

verified ·

1 Parent(s): 57ba142

Initial commit of my fine-tuned model

Browse files

Files changed (5) hide show

README.md +1 -1
adapter_config.json +11 -6
adapter_model.safetensors +1 -1
tokenizer.json +2 -2
tokenizer_config.json +1 -1

README.md CHANGED Viewed

@@ -207,4 +207,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
-- PEFT 0.16.0

 [More Information Needed]
 ### Framework versions
+- PEFT 0.17.1

adapter_config.json CHANGED Viewed

@@ -1,6 +1,10 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
   "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
   "bias": "none",
   "corda_config": null,
@@ -26,13 +30,14 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "q_proj",
     "v_proj",
-    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

 {
   "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
   "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
   "bias": "none",
   "corda_config": null,
   "revision": null,
   "target_modules": [
     "k_proj",
     "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cea07bc9f4b6aa36739e9b43d9839ac81daf221642f1b41003990893654f425
 size 97307544

 version https://git-lfs.github.com/spec/v1
+oid sha256:6ae02d0062f087257d19bf6169788018ad11014e7feaff2243139809b6db4dd3
 size 97307544

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
-size 17210019

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json CHANGED Viewed

@@ -2060,7 +2060,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }

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