Instructions to use Josephgflowers/3BigReasonCinder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Josephgflowers/3BigReasonCinder with Transformers:

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

pipe = pipeline("text-generation", model="Josephgflowers/3BigReasonCinder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Josephgflowers/3BigReasonCinder")
model = AutoModelForCausalLM.from_pretrained("Josephgflowers/3BigReasonCinder")

llama-cpp-python

How to use Josephgflowers/3BigReasonCinder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Josephgflowers/3BigReasonCinder",
	filename="3BigReasonCinder-unsloth.F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Josephgflowers/3BigReasonCinder with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Josephgflowers/3BigReasonCinder:F16
# Run inference directly in the terminal:
llama-cli -hf Josephgflowers/3BigReasonCinder:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Josephgflowers/3BigReasonCinder:F16
# Run inference directly in the terminal:
llama-cli -hf Josephgflowers/3BigReasonCinder:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Josephgflowers/3BigReasonCinder:F16
# Run inference directly in the terminal:
./llama-cli -hf Josephgflowers/3BigReasonCinder:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Josephgflowers/3BigReasonCinder:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Josephgflowers/3BigReasonCinder:F16

Use Docker

docker model run hf.co/Josephgflowers/3BigReasonCinder:F16

LM Studio
Jan

vLLM

How to use Josephgflowers/3BigReasonCinder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Josephgflowers/3BigReasonCinder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/3BigReasonCinder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Josephgflowers/3BigReasonCinder:F16

SGLang

How to use Josephgflowers/3BigReasonCinder 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 "Josephgflowers/3BigReasonCinder" \
    --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": "Josephgflowers/3BigReasonCinder",
		"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 "Josephgflowers/3BigReasonCinder" \
        --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": "Josephgflowers/3BigReasonCinder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Josephgflowers/3BigReasonCinder with Ollama:
```
ollama run hf.co/Josephgflowers/3BigReasonCinder:F16
```

Unsloth Studio

How to use Josephgflowers/3BigReasonCinder 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 Josephgflowers/3BigReasonCinder 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 Josephgflowers/3BigReasonCinder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Josephgflowers/3BigReasonCinder to start chatting

Docker Model Runner
How to use Josephgflowers/3BigReasonCinder with Docker Model Runner:
```
docker model run hf.co/Josephgflowers/3BigReasonCinder:F16
```

Lemonade

How to use Josephgflowers/3BigReasonCinder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Josephgflowers/3BigReasonCinder:F16

Run and chat with the model

lemonade run user.3BigReasonCinder-F16

List all available models

lemonade list

Josephgflowers commited on Feb 7, 2024

Commit

ec1da6e

verified ·

1 Parent(s): 359bf25

Upload config.json

Browse files

Files changed (1) hide show

config.json +7 -4

config.json CHANGED Viewed

@@ -1,8 +1,10 @@
 {
-  "_name_or_path": "MiniChat-2-DPO-3B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -15,14 +17,15 @@
   "num_attention_heads": 24,
   "num_hidden_layers": 24,
   "num_key_value_heads": 24,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.33.2",
   "use_cache": true,
   "vocab_size": 49216
 }

 {
+  "_name_or_path": "/content/3BigReasonCinder",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "num_attention_heads": 24,
   "num_hidden_layers": 24,
   "num_key_value_heads": 24,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "unsloth_version": "2024.2",
   "use_cache": true,
   "vocab_size": 49216
 }