Instructions to use peterbeamish/long_llama_7b_env with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use peterbeamish/long_llama_7b_env with Transformers:

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

pipe = pipeline("text-generation", model="peterbeamish/long_llama_7b_env", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("peterbeamish/long_llama_7b_env", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use peterbeamish/long_llama_7b_env with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peterbeamish/long_llama_7b_env"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "peterbeamish/long_llama_7b_env",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/peterbeamish/long_llama_7b_env

SGLang

How to use peterbeamish/long_llama_7b_env 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 "peterbeamish/long_llama_7b_env" \
    --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": "peterbeamish/long_llama_7b_env",
		"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 "peterbeamish/long_llama_7b_env" \
        --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": "peterbeamish/long_llama_7b_env",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use peterbeamish/long_llama_7b_env with Docker Model Runner:
```
docker model run hf.co/peterbeamish/long_llama_7b_env
```

peterbeamish commited on Nov 23, 2023

Commit

26bd18c

1 Parent(s): 1253454

Training in progress, step 50

Browse files

Files changed (5) hide show

.gitignore +1 -0
config.json +1 -1
runs/Nov23_21-15-28_nom5sn90y1/events.out.tfevents.1700774897.nom5sn90y1.36.0 +3 -0
runs/Nov23_21-39-07_ng8mfl7cg3/events.out.tfevents.1700775555.ng8mfl7cg3.36.0 +3 -0
training_args.bin +3 -0

.gitignore ADDED Viewed

	@@ -0,0 +1 @@


1	+ checkpoint-*/

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "training_output/final_model",
   "architectures": [
     "LongLlamaForCausalLM"
   ],

 {
+  "_name_or_path": "syzymon/long_llama_code_7b_instruct",
   "architectures": [
     "LongLlamaForCausalLM"
   ],

runs/Nov23_21-15-28_nom5sn90y1/events.out.tfevents.1700774897.nom5sn90y1.36.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad6bf3fb3a0a6b621e250fcda8faa1d09f6f6a1adb328dd811434a19c32d29a
+size 4668

runs/Nov23_21-39-07_ng8mfl7cg3/events.out.tfevents.1700775555.ng8mfl7cg3.36.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdb49108b18dd982be236fe9bdeba1be917227ade820e9f95c66c5268b45292
+size 4976

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9838b5c943b7d5bfaa1564f3cb1d1d39426ba5ce14e2b5d0d2fbad801ef1cd73
+size 3951