Instructions to use jphme/em_german_7b_leo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jphme/em_german_7b_leo with Transformers:

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

pipe = pipeline("text-generation", model="jphme/em_german_7b_leo", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jphme/em_german_7b_leo", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jphme/em_german_7b_leo", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jphme/em_german_7b_leo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jphme/em_german_7b_leo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jphme/em_german_7b_leo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jphme/em_german_7b_leo

SGLang

How to use jphme/em_german_7b_leo 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 "jphme/em_german_7b_leo" \
    --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": "jphme/em_german_7b_leo",
		"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 "jphme/em_german_7b_leo" \
        --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": "jphme/em_german_7b_leo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jphme/em_german_7b_leo with Docker Model Runner:
```
docker model run hf.co/jphme/em_german_7b_leo
```

jphme commited on Oct 3, 2023

Commit

9240a02

1 Parent(s): 3320d48

merged model upload

Browse files

Files changed (5) hide show

config.json +1 -1
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1
tokenizer.json +0 -0
tokenizer_config.json +3 -6

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "jphme/em_german_7b_leo2",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "jphme/em_german_7b_leo",
   "architectures": [
     "LlamaForCausalLM"
   ],

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d17712854ab6871d808e07b0f2b01e826748f7a4553b4e18af4c0d987b5bda3
 size 9976570304

 version https://git-lfs.github.com/spec/v1
+oid sha256:e9aa1ed46458ed16e34b218774855ad5f8a247e7cec63f98452d8577b7b2ab51
 size 9976570304

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772d1f2dbb87bf629ee3cee6eea95393a7ae4f6f05a5f475698542635b682714
 size 3500294472

 version https://git-lfs.github.com/spec/v1
+oid sha256:47c9cdc80ecdbd965246e6eac2673d1f1c084c328ab0978f6502365e44db3f5d
 size 3500294472

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -8,7 +6,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     },
     "1": {
       "content": "<s>",
@@ -16,7 +14,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     },
     "2": {
       "content": "</s>",
@@ -24,7 +22,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [],
@@ -38,7 +36,6 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "tokenizer_file": "/root/.cache/huggingface/hub/models--LeoLM--leo-hessianai-7b/snapshots/88c5ac07006ea8f1b5d10aa4f03f0d624dd27e56/tokenizer.json",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }

 {
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     },
     "1": {
       "content": "<s>",
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     },
     "2": {
       "content": "</s>",
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [],
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }