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

Libraries

How to use JaphetHernandez/llama_retrained with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("JaphetHernandez/llama_retrained", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JaphetHernandez/llama_retrained with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/JaphetHernandez/llama_retrained

SGLang

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

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

JaphetHernandez commited on Nov 2, 2024

Commit

3eb5237

verified ·

1 Parent(s): f83223c

Upload model

Browse files

Files changed (2) hide show

adapter_config.json +0 -6
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -20,12 +20,6 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "q_proj",
-    "v_proj",
-    "gate_proj",
-    "down_proj",
     "up_proj"
   ],
   "task_type": "text-generation-inference",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj"
   ],
   "task_type": "text-generation-inference",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31fe56a287680929621dc12b05d80894cba39adb690e1723dcf7733657779f8
-size 2146498720

 version https://git-lfs.github.com/spec/v1
+oid sha256:fe427e8a19b706981fc143476aaad1b7f31b8351c6cb4e0dccbc6e976100fb1a
+size 1061179520