Instructions to use subset-data/falcon-7b-bt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use subset-data/falcon-7b-bt with Transformers:

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

pipe = pipeline("text-generation", model="subset-data/falcon-7b-bt", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("subset-data/falcon-7b-bt", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use subset-data/falcon-7b-bt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "subset-data/falcon-7b-bt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "subset-data/falcon-7b-bt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/subset-data/falcon-7b-bt

SGLang

How to use subset-data/falcon-7b-bt 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 "subset-data/falcon-7b-bt" \
    --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": "subset-data/falcon-7b-bt",
		"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 "subset-data/falcon-7b-bt" \
        --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": "subset-data/falcon-7b-bt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use subset-data/falcon-7b-bt with Docker Model Runner:
```
docker model run hf.co/subset-data/falcon-7b-bt
```

brian-todd commited on Jul 20, 2023

Commit

0b2ffef

1 Parent(s): f18cbcf

Training in progress, step 50

Browse files

Files changed (6) hide show

adapter_model.bin +1 -1
last-checkpoint/adapter_model.bin +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 +9 -3

adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078b1dc9fabb8ff91dd19e84ca5db3689da687933839f8ebed3eb3184d44da8d
 size 522284877

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1a71b7e8ae14c88580ffe0c1360c7b1d7b239f3ab94197c8ead5dc7f25854f7
 size 522284877

last-checkpoint/adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078b1dc9fabb8ff91dd19e84ca5db3689da687933839f8ebed3eb3184d44da8d
 size 522284877

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1a71b7e8ae14c88580ffe0c1360c7b1d7b239f3ab94197c8ead5dc7f25854f7
 size 522284877

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6aa0a7fb937b4e4bf00948795f37bee419b0b095bf52c8302f13bb33a42ee98
 size 1044539653

 version https://git-lfs.github.com/spec/v1
+oid sha256:8e36f5aaedc3e994e5a0b5836bb0af44c0240b862ef82790903277995a57f376
 size 1044539653

last-checkpoint/rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3cc8f6adfa37668329da8447a85e6a651210c7a720a96daffe48a1fa82f62ad
 size 14575

 version https://git-lfs.github.com/spec/v1
+oid sha256:2d6a8c64876e8da440a44b8c8a6303391d2df910fb7ef6369f4e69af17f4179e
 size 14575

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07b799de8e7cd21f3d80f252f90d463af2ea3da63f9b744b2d71ed8e917819e
 size 627

 version https://git-lfs.github.com/spec/v1
+oid sha256:d217edb059555be97837810de03dc22d79976c8832aac609d084f6016b5003c4
 size 627

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
-  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,11 +30,17 @@
       "learning_rate": 0.0002,
       "loss": 0.0961,
       "step": 40
     }
   ],
   "max_steps": 200,
   "num_train_epochs": 50,
-  "total_flos": 1.30768392093696e+16,
   "trial_name": null,
   "trial_params": null
 }

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 12.5,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "learning_rate": 0.0002,
       "loss": 0.0961,
       "step": 40
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0536,
+      "step": 50
     }
   ],
   "max_steps": 200,
   "num_train_epochs": 50,
+  "total_flos": 1.635642745552896e+16,
   "trial_name": null,
   "trial_params": null
 }