Instructions to use Ba2han/model-sft-q2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/model-sft-q2 with Transformers:

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

pipe = pipeline("text-generation", model="Ba2han/model-sft-q2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ba2han/model-sft-q2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Ba2han/model-sft-q2", trust_remote_code=True)
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 Ba2han/model-sft-q2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/model-sft-q2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/model-sft-q2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/model-sft-q2

SGLang

How to use Ba2han/model-sft-q2 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 "Ba2han/model-sft-q2" \
    --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": "Ba2han/model-sft-q2",
		"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 "Ba2han/model-sft-q2" \
        --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": "Ba2han/model-sft-q2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Ba2han/model-sft-q2 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 Ba2han/model-sft-q2 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 Ba2han/model-sft-q2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/model-sft-q2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/model-sft-q2",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/model-sft-q2 with Docker Model Runner:
```
docker model run hf.co/Ba2han/model-sft-q2
```

Ba2han commited on 2 days ago

Commit

fff8ec6

verified ·

1 Parent(s): 441015c

Training in progress, step 7043

Browse files

Files changed (3) hide show

generation_config.json +1 -1
model.safetensors +1 -1
tokenizer_config.json +1 -1

generation_config.json CHANGED Viewed

@@ -8,7 +8,7 @@
   "max_length": 8192,
   "output_attentions": false,
   "output_hidden_states": false,
-  "pad_token_id": 50049,
   "transformers_version": "5.5.0",
   "use_cache": false
 }

   "max_length": 8192,
   "output_attentions": false,
   "output_hidden_states": false,
+  "pad_token_id": 50034,
   "transformers_version": "5.5.0",
   "use_cache": false
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead1ffa66fefc73d009e2283dd80283791464d453a0775b2de6554a6a8802359
 size 1049614696

 version https://git-lfs.github.com/spec/v1
+oid sha256:830c6e82e873a112a37dd424f4f371fe20d8a3252d03b78bfd3e287c8de3d81a
 size 1049614696

tokenizer_config.json CHANGED Viewed

@@ -15,7 +15,7 @@
   "model_max_length": 8192,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null,
   "added_tokens_decoder": {
     "50030": {

   "model_max_length": 8192,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
   "unk_token": null,
   "added_tokens_decoder": {
     "50030": {