Instructions to use thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24 with Transformers:

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

pipe = pipeline("text-generation", model="thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24

SGLang

How to use thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24 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 "thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24" \
    --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": "thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24",
		"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 "thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24" \
        --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": "thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24 with Docker Model Runner:
```
docker model run hf.co/thrunlab/sparse_llama_7b_refined_web_50p_2024-03-24
```

lukeleeai commited on Mar 24, 2024

Commit

49f8e17

verified ·

1 Parent(s): ce72986

Training in progress, step 1000

Browse files

Files changed (3) hide show

adapter_config.json +3 -3
adapter_model.safetensors +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -19,11 +19,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
     "q_proj",
-    "gate_proj",
-    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "up_proj",
     "q_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847f5234740c788e516909721cedc588bb3c2829c0531309c1c6702737edeea4
 size 252750032

 version https://git-lfs.github.com/spec/v1
+oid sha256:167ed9b81c8821119f9ff77cb9484d21e626710622e6c7cd9c1c620a3b461156
 size 252750032

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b291ec0df94e5e0ffc1f97e3f9a061aff604d90a6b2ce7c85d8bae219248dd
 size 6456

 version https://git-lfs.github.com/spec/v1
+oid sha256:de5d7089c5b16560ea374115bb851d690510fb2d3ff2b940ef3d4b8d5b2620a2
 size 6456