Instructions to use flytech/Ruckus-7b-ALPHA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flytech/Ruckus-7b-ALPHA with Transformers:

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

pipe = pipeline("text-generation", model="flytech/Ruckus-7b-ALPHA", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("flytech/Ruckus-7b-ALPHA", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("flytech/Ruckus-7b-ALPHA", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flytech/Ruckus-7b-ALPHA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flytech/Ruckus-7b-ALPHA"
# 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-7b-ALPHA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flytech/Ruckus-7b-ALPHA

SGLang

How to use flytech/Ruckus-7b-ALPHA 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-7b-ALPHA" \
    --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-7b-ALPHA",
		"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-7b-ALPHA" \
        --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-7b-ALPHA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flytech/Ruckus-7b-ALPHA with Docker Model Runner:
```
docker model run hf.co/flytech/Ruckus-7b-ALPHA
```

flytech commited on Sep 19, 2023

Commit

56df1f4

1 Parent(s): 94974d5

Training in progress, step 900, 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 sha256:402576c87180344206acae5fcf619df208f359329377bdd0107171982e317c56
 size 67143296

 version https://git-lfs.github.com/spec/v1
+oid sha256:625c24ad2702a76c58af2535cf9c27d049e84fb7e01989449430541b3b0fbfce
 size 67143296

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026521f3d6159fef03020641ca43a68180d979cb9fa205e50135e79bf63e71d5
 size 33920095

 version https://git-lfs.github.com/spec/v1
+oid sha256:9478eb7b3f3027bb4070c6389e3eba25e44251abcc324317c1e9a1079f1fc04b
 size 33920095

last-checkpoint/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e8faac1b72cc7bf9f026c349ca080abc19142b09be6f278cd43911aa1397ba
 size 14575

 version https://git-lfs.github.com/spec/v1
+oid sha256:518e379eb95b8761d691fa2f3663a7e6b2114c816fd3f33c63e566311da0ce7c
 size 14575

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f97bf5fc062ac3e4a876a0097c0718f2e93d4749d37498e737b83f15731a48
 size 627

 version https://git-lfs.github.com/spec/v1
+oid sha256:4c1c649bd14a49756b729525a4732fa77be1d6c78a716ad6162c210414e48318
 size 627

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.878048780487805,
   "eval_steps": 100,
-  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,13 +111,26 @@
       "eval_samples_per_second": 2.038,
       "eval_steps_per_second": 0.266,
       "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 1312,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 6.644896574629478e+16,
   "trial_name": null,
   "trial_params": null
 }

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 5.487804878048781,
   "eval_steps": 100,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 2.038,
       "eval_steps_per_second": 0.266,
       "step": 800
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 0.0002,
+      "loss": 0.0356,
+      "step": 900
+    },
+    {
+      "epoch": 5.49,
+      "eval_runtime": 33.8728,
+      "eval_samples_per_second": 2.037,
+      "eval_steps_per_second": 0.266,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 1312,
   "num_train_epochs": 8,
   "save_steps": 100,
+  "total_flos": 7.473948323217408e+16,
   "trial_name": null,
   "trial_params": null
 }