Instructions to use openlamm/lamm_7b_lora32_98k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlamm/lamm_7b_lora32_98k with Transformers:

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

pipe = pipeline("text-generation", model="openlamm/lamm_7b_lora32_98k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlamm/lamm_7b_lora32_98k")
model = AutoModelForCausalLM.from_pretrained("openlamm/lamm_7b_lora32_98k")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openlamm/lamm_7b_lora32_98k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openlamm/lamm_7b_lora32_98k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openlamm/lamm_7b_lora32_98k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlamm/lamm_7b_lora32_98k

SGLang

How to use openlamm/lamm_7b_lora32_98k 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 "openlamm/lamm_7b_lora32_98k" \
    --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": "openlamm/lamm_7b_lora32_98k",
		"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 "openlamm/lamm_7b_lora32_98k" \
        --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": "openlamm/lamm_7b_lora32_98k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlamm/lamm_7b_lora32_98k with Docker Model Runner:
```
docker model run hf.co/openlamm/lamm_7b_lora32_98k
```

openlamm commited on Jul 28, 2023

Commit

4e92366

1 Parent(s): 0d98970

Upload 5 files

Browse files

Files changed (2) hide show

config.json +1 -1
pytorch_model.pt +1 -1

config.json CHANGED Viewed

@@ -18,7 +18,7 @@
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.29.1",
   "use_cache": true,
   "vocab_size": 32001
 }

   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.30.0",
   "use_cache": true,
   "vocab_size": 32001
 }

pytorch_model.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7393d2ccc71aca4ebe9550ebaed5397742ea8ee0790ba0a2287cdd16a76dd9c4
 size 75557931

 version https://git-lfs.github.com/spec/v1
+oid sha256:6fb861e7cc14d88fb6ee83e2fa984a32e5a77e7dc37077ce83bc0343ffc93d53
 size 75557931