Instructions to use Jordansky/SFTSmoke-GR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Jordansky/SFTSmoke-GR with PEFT:
```
Base model is not found.
```

How to use Jordansky/SFTSmoke-GR with Transformers:

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

pipe = pipeline("text-generation", model="Jordansky/SFTSmoke-GR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jordansky/SFTSmoke-GR", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jordansky/SFTSmoke-GR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jordansky/SFTSmoke-GR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jordansky/SFTSmoke-GR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jordansky/SFTSmoke-GR

SGLang

How to use Jordansky/SFTSmoke-GR 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 "Jordansky/SFTSmoke-GR" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jordansky/SFTSmoke-GR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Jordansky/SFTSmoke-GR" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jordansky/SFTSmoke-GR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jordansky/SFTSmoke-GR with Docker Model Runner:
```
docker model run hf.co/Jordansky/SFTSmoke-GR
```

Jordansky commited on May 4

Commit

4dbfaad

verified ·

1 Parent(s): 3abcc1c

Upload task output 1

Browse files

Files changed (5) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1
loss.txt +1 -1
trainer_state.json +0 -0
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -30,12 +30,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj",
     "down_proj",
-    "o_proj",
-    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "revision": null,
   "target_modules": [
     "up_proj",
+    "k_proj",
     "q_proj",
     "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb222b8d7bdf1007263d27c5a5359bec6fe9351318e557ec7471906603e42168
 size 319876032

 version https://git-lfs.github.com/spec/v1
+oid sha256:9b72e600a1df02248f15963c3d348222177175cca57d3f3c90c788e1e99ae01e
 size 319876032

loss.txt CHANGED Viewed

	@@ -1 +1 @@
1	- ~~150~~,no_eval


1	+ 43,no_eval

trainer_state.json CHANGED Viewed

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

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d757ad2fe14b7897b2d77022b7ff4223a819f859132e88cb7febd65fbeb43d0
 size 8081

 version https://git-lfs.github.com/spec/v1
+oid sha256:e643070ce959bccb245b15540824bcb063c8b830035cf64fbe56348a92d96db9
 size 8081