Instructions to use ale045/kaggle_math_model_v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ale045/kaggle_math_model_v6 with Transformers:

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

pipe = pipeline("text-generation", model="ale045/kaggle_math_model_v6")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ale045/kaggle_math_model_v6")
model = AutoModelForCausalLM.from_pretrained("ale045/kaggle_math_model_v6", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ale045/kaggle_math_model_v6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ale045/kaggle_math_model_v6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ale045/kaggle_math_model_v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ale045/kaggle_math_model_v6

SGLang

How to use ale045/kaggle_math_model_v6 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 "ale045/kaggle_math_model_v6" \
    --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": "ale045/kaggle_math_model_v6",
		"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 "ale045/kaggle_math_model_v6" \
        --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": "ale045/kaggle_math_model_v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use ale045/kaggle_math_model_v6 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 ale045/kaggle_math_model_v6 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 ale045/kaggle_math_model_v6 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ale045/kaggle_math_model_v6 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ale045/kaggle_math_model_v6",
    max_seq_length=2048,
)

Docker Model Runner
How to use ale045/kaggle_math_model_v6 with Docker Model Runner:
```
docker model run hf.co/ale045/kaggle_math_model_v6
```

ale045 commited on Jun 7, 2024

Commit

b44be1f

verified ·

1 Parent(s): ef781fc

Trained with Unsloth

Browse files

Files changed (5) hide show

config.json +6 -2
model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ale045/kaggle_math_model_v6",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -17,9 +17,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",

 {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128255,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 1.5,
+    "type": "linear"
+  },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8320a464ed41961626f5db5f04be58e73dd8ff09064844293219f51db3a82b
 size 4976698672

 version https://git-lfs.github.com/spec/v1
+oid sha256:5f570b49215254c2f59b7c7c78b84667be6592c34edc43d3b21a6568b4470e89
 size 4976698672

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139719d7110a6dd9634f9fe3c39fa6633dafb21c968d34e9df15137dc31f89b1
 size 4999802720

 version https://git-lfs.github.com/spec/v1
+oid sha256:8b955c8213fabc1320bd3ee4d69124f72d7e7178b0c769ee67995f849cbd641e
 size 4999802720

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca9c591d53b39102a906c017ef308d0d9d41920922157c2b7d3b9cb62acfda0
 size 4915916176

 version https://git-lfs.github.com/spec/v1
+oid sha256:0ba1231da86c3cf7907f30f0c9adbfffce09babd5617ced6f89b22c30fb10791
 size 4915916176

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8519472654251766e8b20c08462409bdfcfcb2af79882af5401bf6e61d53c46
 size 1168138808

 version https://git-lfs.github.com/spec/v1
+oid sha256:5a4f031d2d22252e55bcaa3172f28371c9b1c8d26e162aff4ccff5d88480a506
 size 1168138808