Instructions to use trex5790/model_l1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trex5790/model_l1 with Transformers:

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

pipe = pipeline("text-generation", model="trex5790/model_l1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trex5790/model_l1")
model = AutoModelForCausalLM.from_pretrained("trex5790/model_l1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trex5790/model_l1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trex5790/model_l1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trex5790/model_l1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/trex5790/model_l1

SGLang

How to use trex5790/model_l1 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 "trex5790/model_l1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trex5790/model_l1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "trex5790/model_l1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trex5790/model_l1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use trex5790/model_l1 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 trex5790/model_l1 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 trex5790/model_l1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for trex5790/model_l1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="trex5790/model_l1",
    max_seq_length=2048,
)

Docker Model Runner
How to use trex5790/model_l1 with Docker Model Runner:
```
docker model run hf.co/trex5790/model_l1
```

trex5790 commited on Apr 30, 2024

Commit

a38b5f6

verified ·

1 Parent(s): 00732ed

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -19,7 +19,7 @@
   "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "gptq",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
@@ -27,7 +27,7 @@
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
     "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

   "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
     "load_in_8bit": false,
+    "quant_method": "gptq"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,