Instructions to use codesagar/WatchTowerReasoning_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codesagar/WatchTowerReasoning_4bit with Transformers:

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

pipe = pipeline("text-generation", model="codesagar/WatchTowerReasoning_4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codesagar/WatchTowerReasoning_4bit")
model = AutoModelForCausalLM.from_pretrained("codesagar/WatchTowerReasoning_4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codesagar/WatchTowerReasoning_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codesagar/WatchTowerReasoning_4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codesagar/WatchTowerReasoning_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codesagar/WatchTowerReasoning_4bit

SGLang

How to use codesagar/WatchTowerReasoning_4bit 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 "codesagar/WatchTowerReasoning_4bit" \
    --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": "codesagar/WatchTowerReasoning_4bit",
		"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 "codesagar/WatchTowerReasoning_4bit" \
        --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": "codesagar/WatchTowerReasoning_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use codesagar/WatchTowerReasoning_4bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for codesagar/WatchTowerReasoning_4bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for codesagar/WatchTowerReasoning_4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for codesagar/WatchTowerReasoning_4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="codesagar/WatchTowerReasoning_4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use codesagar/WatchTowerReasoning_4bit with Docker Model Runner:
```
docker model run hf.co/codesagar/WatchTowerReasoning_4bit
```

codesagar commited on Aug 13, 2024

Commit

4835a1c

verified ·

1 Parent(s): 946b81e

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

tokenizer.json +7 -16
tokenizer_config.json +2 -1

tokenizer.json CHANGED Viewed

@@ -31,23 +31,13 @@
       "special": true
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -134,6 +124,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

       "special": true
     }
   ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -31,7 +32,7 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
   "model_max_length": 32768,
   "pad_token": "<unk>",
   "padding_side": "left",

 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "legacy": false,
   "model_max_length": 32768,
   "pad_token": "<unk>",
   "padding_side": "left",