Instructions to use flytech/Ruckus-13b-27 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flytech/Ruckus-13b-27 with Transformers:

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

pipe = pipeline("text-generation", model="flytech/Ruckus-13b-27")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flytech/Ruckus-13b-27")
model = AutoModelForCausalLM.from_pretrained("flytech/Ruckus-13b-27", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flytech/Ruckus-13b-27 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flytech/Ruckus-13b-27"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flytech/Ruckus-13b-27",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flytech/Ruckus-13b-27

SGLang

How to use flytech/Ruckus-13b-27 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 "flytech/Ruckus-13b-27" \
    --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": "flytech/Ruckus-13b-27",
		"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 "flytech/Ruckus-13b-27" \
        --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": "flytech/Ruckus-13b-27",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flytech/Ruckus-13b-27 with Docker Model Runner:
```
docker model run hf.co/flytech/Ruckus-13b-27
```

flytech commited on Sep 28, 2023

Commit

3591e98

1 Parent(s): da0d1a0

Training in progress, step 2200, checkpoint

Browse files

Files changed (5) hide show

last-checkpoint/adapter_model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/rng_state.pth +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +16 -3

last-checkpoint/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8459b9f832ef25a417640bf0233bf837cd58164df9c457efc3e290ab0e68c964
 size 250422888

 version https://git-lfs.github.com/spec/v1
+oid sha256:a3879db05063c5090ff0412004f6af70c6c85cc0ca75b514895ac158cf7402f3
 size 250422888

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb024f66bab43727577e41564d8e9829a6ce8f78c8ff35fab9e27a566b312a2
 size 126034975

 version https://git-lfs.github.com/spec/v1
+oid sha256:67271ad9d0d1fc2156dc075da167c0ed7deeda4c41573a8d093b70c4bb883372
 size 126034975

last-checkpoint/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0a527772fa484fe0f5b977a5f9514063f30bbaa2addc71ee53b83bf0f23343
 size 14575

 version https://git-lfs.github.com/spec/v1
+oid sha256:17d896dbcbd4ca31eb08b7a70f5410cdc580dd613e857d91f68a6a2645d0af9f
 size 14575

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

 version https://git-lfs.github.com/spec/v1
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.70873786407767,
   "eval_steps": 200,
-  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,13 +137,26 @@
       "eval_samples_per_second": 7.932,
       "eval_steps_per_second": 0.504,
       "step": 2000
     }
   ],
   "logging_steps": 200,
   "max_steps": 2472,
   "num_train_epochs": 12,
   "save_steps": 200,
-  "total_flos": 6.439303461470208e+17,
   "trial_name": null,
   "trial_params": null
 }

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 10.679611650485437,
   "eval_steps": 200,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 7.932,
       "eval_steps_per_second": 0.504,
       "step": 2000
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0258,
+      "step": 2200
+    },
+    {
+      "epoch": 10.68,
+      "eval_runtime": 21.7533,
+      "eval_samples_per_second": 7.953,
+      "eval_steps_per_second": 0.506,
+      "step": 2200
     }
   ],
   "logging_steps": 200,
   "max_steps": 2472,
   "num_train_epochs": 12,
   "save_steps": 200,
+  "total_flos": 7.08301176963072e+17,
   "trial_name": null,
   "trial_params": null
 }