Instructions to use freewheelin/free-solar-instrunction-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use freewheelin/free-solar-instrunction-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="freewheelin/free-solar-instrunction-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("freewheelin/free-solar-instrunction-v0.1")
model = AutoModelForCausalLM.from_pretrained("freewheelin/free-solar-instrunction-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use freewheelin/free-solar-instrunction-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "freewheelin/free-solar-instrunction-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "freewheelin/free-solar-instrunction-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/freewheelin/free-solar-instrunction-v0.1

SGLang

How to use freewheelin/free-solar-instrunction-v0.1 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 "freewheelin/free-solar-instrunction-v0.1" \
    --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": "freewheelin/free-solar-instrunction-v0.1",
		"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 "freewheelin/free-solar-instrunction-v0.1" \
        --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": "freewheelin/free-solar-instrunction-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use freewheelin/free-solar-instrunction-v0.1 with Docker Model Runner:
```
docker model run hf.co/freewheelin/free-solar-instrunction-v0.1
```

freewheelin commited on Mar 14, 2024

Commit

a651e53

verified ·

1 Parent(s): 90332a2

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +1 -6
tokenizer_config.json +1 -5

tokenizer.json CHANGED Viewed

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 4096,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json CHANGED Viewed

@@ -128032,17 +128032,13 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "legacy": true,
-  "max_length": 4096,
   "model_max_length": 4096,
   "pad_token": "</s>",
-  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "split_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "trust_remote_code": false,
   "unk_token": "<unk>",
   "use_default_system_prompt": true,

   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "legacy": true,
   "model_max_length": 4096,
   "pad_token": "</s>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "split_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "trust_remote_code": false,
   "unk_token": "<unk>",
   "use_default_system_prompt": true,