Instructions to use tanmaymane18/cnc_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tanmaymane18/cnc_lora with Transformers:

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

pipe = pipeline("text-generation", model="tanmaymane18/cnc_lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tanmaymane18/cnc_lora")
model = AutoModelForCausalLM.from_pretrained("tanmaymane18/cnc_lora", 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 tanmaymane18/cnc_lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanmaymane18/cnc_lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tanmaymane18/cnc_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanmaymane18/cnc_lora

SGLang

How to use tanmaymane18/cnc_lora 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 "tanmaymane18/cnc_lora" \
    --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": "tanmaymane18/cnc_lora",
		"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 "tanmaymane18/cnc_lora" \
        --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": "tanmaymane18/cnc_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use tanmaymane18/cnc_lora 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 tanmaymane18/cnc_lora 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 tanmaymane18/cnc_lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tanmaymane18/cnc_lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="tanmaymane18/cnc_lora",
    max_seq_length=2048,
)

Docker Model Runner
How to use tanmaymane18/cnc_lora with Docker Model Runner:
```
docker model run hf.co/tanmaymane18/cnc_lora
```

tanmaymane18 commited on Dec 29, 2024

Commit

27832ab

verified ·

1 Parent(s): 8707ef3

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +6 -6
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 4,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
@@ -26,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
     "k_proj",
-    "gate_proj",
     "up_proj",
     "o_proj",
-    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-3.2-3b-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
+    "v_proj",
+    "q_proj",
     "up_proj",
+    "gate_proj",
     "o_proj",
+    "down_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 sha256:84cbd810f763c149e40c12bc496e09104d228d831a6e2d295b585fc8dec4daad
 size 7800411520

 version https://git-lfs.github.com/spec/v1
+oid sha256:c48a7e7e5b8d9fe605e04e4d720d902b1fe2e49285a7accf200f4cb0cde35262
 size 7800411520