Instructions to use TeeA/codeLlama_text2sql_word_r4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeA/codeLlama_text2sql_word_r4 with Transformers:

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

pipe = pipeline("text-generation", model="TeeA/codeLlama_text2sql_word_r4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeeA/codeLlama_text2sql_word_r4")
model = AutoModelForCausalLM.from_pretrained("TeeA/codeLlama_text2sql_word_r4")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TeeA/codeLlama_text2sql_word_r4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeeA/codeLlama_text2sql_word_r4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeeA/codeLlama_text2sql_word_r4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TeeA/codeLlama_text2sql_word_r4

SGLang

How to use TeeA/codeLlama_text2sql_word_r4 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 "TeeA/codeLlama_text2sql_word_r4" \
    --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": "TeeA/codeLlama_text2sql_word_r4",
		"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 "TeeA/codeLlama_text2sql_word_r4" \
        --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": "TeeA/codeLlama_text2sql_word_r4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TeeA/codeLlama_text2sql_word_r4 with Docker Model Runner:
```
docker model run hf.co/TeeA/codeLlama_text2sql_word_r4
```

TeeA commited on Apr 17, 2024

Commit

019eb82

verified ·

1 Parent(s): c678aad

Training in progress, step 55400

Browse files

Files changed (5) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1
runs/Apr15_12-13-10_kao-dgxa-e10-u17/events.out.tfevents.1713179608.kao-dgxa-e10-u17.2134547.1 +2 -2
runs/Apr17_12-31-21_kao-dgxa-e10-u17/events.out.tfevents.1713353547.kao-dgxa-e10-u17.3360862.0 +3 -0
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "k_proj",
     "up_proj",
     "q_proj",
     "v_proj",
-    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

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

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b58724735eff101b2bee1b56132cf63f2e497112d192c3a4f28397dc125b295
 size 40036040

 version https://git-lfs.github.com/spec/v1
+oid sha256:122bca2d08bae51b7f8c1e8e19c4c808064512f73a9f9ed728a3f8f9a3dffeb2
 size 40036040

runs/Apr15_12-13-10_kao-dgxa-e10-u17/events.out.tfevents.1713179608.kao-dgxa-e10-u17.2134547.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0243c132ff65a46d21e39ff7581048d3150ac4be71f692ca58d575cb97139e
-size 11882940

 version https://git-lfs.github.com/spec/v1
+oid sha256:b669d6611402de950676eca5e3a3faa7dc6bd8d61b8adc97437cefe939a37753
+size 11920995

runs/Apr17_12-31-21_kao-dgxa-e10-u17/events.out.tfevents.1713353547.kao-dgxa-e10-u17.3360862.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:149e5cd124e553fbcdb1f6b201022b7ced2f620819211856db756495eaa27081
+size 48485

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60bddeed168e5bb4e526b067508b7221a825fe75e69b8d5b0f980f18abcb75a1
 size 5048

 version https://git-lfs.github.com/spec/v1
+oid sha256:38244bfa5665b76fdc9ad0f5c046a18de9b03f57be9d1025e2e2b929555f6c62
 size 5048