Instructions to use jkhouja/Llama-3.2-1B-Instruct_ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jkhouja/Llama-3.2-1B-Instruct_ft with Transformers:

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

pipe = pipeline("text-generation", model="jkhouja/Llama-3.2-1B-Instruct_ft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jkhouja/Llama-3.2-1B-Instruct_ft")
model = AutoModelForCausalLM.from_pretrained("jkhouja/Llama-3.2-1B-Instruct_ft")

Inference
Local Apps Settings

vLLM

How to use jkhouja/Llama-3.2-1B-Instruct_ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jkhouja/Llama-3.2-1B-Instruct_ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jkhouja/Llama-3.2-1B-Instruct_ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jkhouja/Llama-3.2-1B-Instruct_ft

SGLang

How to use jkhouja/Llama-3.2-1B-Instruct_ft 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 "jkhouja/Llama-3.2-1B-Instruct_ft" \
    --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": "jkhouja/Llama-3.2-1B-Instruct_ft",
		"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 "jkhouja/Llama-3.2-1B-Instruct_ft" \
        --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": "jkhouja/Llama-3.2-1B-Instruct_ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jkhouja/Llama-3.2-1B-Instruct_ft with Docker Model Runner:
```
docker model run hf.co/jkhouja/Llama-3.2-1B-Instruct_ft
```

jkhouja commited on Jan 4, 2025

Commit

640f284

verified ·

1 Parent(s): 4f49622

Upload LlamaForCausalLM

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -36,5 +36,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.1",
   "use_cache": true,
-  "vocab_size": 128256
 }

   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.1",
   "use_cache": true,
+  "vocab_size": 128257
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdae1307372edf8829218c69bf4dd65dce69dd3aefbe80fcc30738da24ef59d3
-size 2471645608

 version https://git-lfs.github.com/spec/v1
+oid sha256:b67b6267e3e08a15ee0b1bedbb455b3c2443e5774ad3adba60321b8592bb6627
+size 2471649704