Instructions to use kevin009/llama3math-s90 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kevin009/llama3math-s90 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kevin009/llama3math-s90", dtype="auto")

llama-cpp-python

How to use kevin009/llama3math-s90 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kevin009/llama3math-s90",
	filename="llama3math-s90-unsloth.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use kevin009/llama3math-s90 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kevin009/llama3math-s90:Q8_0
# Run inference directly in the terminal:
llama-cli -hf kevin009/llama3math-s90:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kevin009/llama3math-s90:Q8_0
# Run inference directly in the terminal:
llama-cli -hf kevin009/llama3math-s90:Q8_0

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 kevin009/llama3math-s90:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf kevin009/llama3math-s90:Q8_0

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 kevin009/llama3math-s90:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kevin009/llama3math-s90:Q8_0

Use Docker

docker model run hf.co/kevin009/llama3math-s90:Q8_0

LM Studio
Jan
Ollama
How to use kevin009/llama3math-s90 with Ollama:
```
ollama run hf.co/kevin009/llama3math-s90:Q8_0
```

Unsloth Studio new

How to use kevin009/llama3math-s90 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 kevin009/llama3math-s90 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 kevin009/llama3math-s90 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kevin009/llama3math-s90 to start chatting

Docker Model Runner
How to use kevin009/llama3math-s90 with Docker Model Runner:
```
docker model run hf.co/kevin009/llama3math-s90:Q8_0
```

Lemonade

How to use kevin009/llama3math-s90 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kevin009/llama3math-s90:Q8_0

Run and chat with the model

lemonade run user.llama3math-s90-Q8_0

List all available models

lemonade list

kevin009 commited on Apr 22, 2024

Commit

cbc7dfa

verified ·

1 Parent(s): 8f5b81b

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show

config.json +12 -0
model-00001-of-00002.safetensors +3 -0
model-00002-of-00002.safetensors +3 -0
model.safetensors.index.json +0 -0

config.json CHANGED Viewed

@@ -17,6 +17,18 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 2.0,

   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 2.0,

model-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2e598862e9e45837ae66ddca1f2b24b375934f15f59c5b7c9245d6d9e6d74fa2
+size 4652072943

model-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5394fe848f6eafef2a44f085e7b72e5ef0d315f98aa87b3827c2b1e6983b89
+size 1050673280

model.safetensors.index.json CHANGED Viewed

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