Instructions to use Dogge/Tia-70B-RP-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dogge/Tia-70B-RP-4bit with Transformers:

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

pipe = pipeline("text-generation", model="Dogge/Tia-70B-RP-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Dogge/Tia-70B-RP-4bit")
model = AutoModelForMultimodalLM.from_pretrained("Dogge/Tia-70B-RP-4bit")
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 Dogge/Tia-70B-RP-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dogge/Tia-70B-RP-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dogge/Tia-70B-RP-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dogge/Tia-70B-RP-4bit

SGLang

How to use Dogge/Tia-70B-RP-4bit 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 "Dogge/Tia-70B-RP-4bit" \
    --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": "Dogge/Tia-70B-RP-4bit",
		"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 "Dogge/Tia-70B-RP-4bit" \
        --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": "Dogge/Tia-70B-RP-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Dogge/Tia-70B-RP-4bit 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 Dogge/Tia-70B-RP-4bit 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 Dogge/Tia-70B-RP-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Dogge/Tia-70B-RP-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Dogge/Tia-70B-RP-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use Dogge/Tia-70B-RP-4bit with Docker Model Runner:
```
docker model run hf.co/Dogge/Tia-70B-RP-4bit
```

Dogge commited on Apr 20, 2024

Commit

17616f9

verified ·

1 Parent(s): 1c19377

Upload 3 files

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -4
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,

   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,

generation_config.json CHANGED Viewed

@@ -1,9 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128009
-  ],
   "transformers_version": "4.40.0"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 128000,
+  "eos_token_id": 128009,
   "transformers_version": "4.40.0"
 }

tokenizer_config.json CHANGED Viewed

@@ -2052,7 +2052,7 @@
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"

   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"