Instructions to use GaussianMixture/CodeLlama-34b-Instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GaussianMixture/CodeLlama-34b-Instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="GaussianMixture/CodeLlama-34b-Instruct-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GaussianMixture/CodeLlama-34b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("GaussianMixture/CodeLlama-34b-Instruct-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GaussianMixture/CodeLlama-34b-Instruct-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GaussianMixture/CodeLlama-34b-Instruct-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GaussianMixture/CodeLlama-34b-Instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GaussianMixture/CodeLlama-34b-Instruct-hf

SGLang

How to use GaussianMixture/CodeLlama-34b-Instruct-hf 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 "GaussianMixture/CodeLlama-34b-Instruct-hf" \
    --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": "GaussianMixture/CodeLlama-34b-Instruct-hf",
		"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 "GaussianMixture/CodeLlama-34b-Instruct-hf" \
        --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": "GaussianMixture/CodeLlama-34b-Instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GaussianMixture/CodeLlama-34b-Instruct-hf with Docker Model Runner:
```
docker model run hf.co/GaussianMixture/CodeLlama-34b-Instruct-hf
```

GaussianMixture commited on Aug 24, 2023

Commit

f3eedfc

1 Parent(s): 79c1d04

Update config.json

Browse files

Files changed (1) hide show

config.json +4 -1

config.json CHANGED Viewed

@@ -17,7 +17,10 @@
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",

   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "type": "linear",
+    "factor": 4.0
+  },
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",