Instructions to use bufanlin/Phi3_Chinese_Main with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bufanlin/Phi3_Chinese_Main with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bufanlin/Phi3_Chinese_Main", dtype="auto")

llama-cpp-python

How to use bufanlin/Phi3_Chinese_Main with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bufanlin/Phi3_Chinese_Main",
	filename="Phi3_Chinese_Main-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 bufanlin/Phi3_Chinese_Main with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bufanlin/Phi3_Chinese_Main:Q8_0
# Run inference directly in the terminal:
llama-cli -hf bufanlin/Phi3_Chinese_Main:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bufanlin/Phi3_Chinese_Main:Q8_0
# Run inference directly in the terminal:
llama-cli -hf bufanlin/Phi3_Chinese_Main: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 bufanlin/Phi3_Chinese_Main:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf bufanlin/Phi3_Chinese_Main: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 bufanlin/Phi3_Chinese_Main:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bufanlin/Phi3_Chinese_Main:Q8_0

Use Docker

docker model run hf.co/bufanlin/Phi3_Chinese_Main:Q8_0

LM Studio
Jan
Ollama
How to use bufanlin/Phi3_Chinese_Main with Ollama:
```
ollama run hf.co/bufanlin/Phi3_Chinese_Main:Q8_0
```

Unsloth Studio new

How to use bufanlin/Phi3_Chinese_Main 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 bufanlin/Phi3_Chinese_Main 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 bufanlin/Phi3_Chinese_Main to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bufanlin/Phi3_Chinese_Main to start chatting

Docker Model Runner
How to use bufanlin/Phi3_Chinese_Main with Docker Model Runner:
```
docker model run hf.co/bufanlin/Phi3_Chinese_Main:Q8_0
```

Lemonade

How to use bufanlin/Phi3_Chinese_Main with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bufanlin/Phi3_Chinese_Main:Q8_0

Run and chat with the model

lemonade run user.Phi3_Chinese_Main-Q8_0

List all available models

lemonade list

bufanlin commited on May 19, 2024

Commit

2851c93

verified ·

1 Parent(s): 3f19889

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show

adapter_config.json +5 -5
adapter_model.safetensors +2 -2
generation_config.json +6 -4

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,12 +21,12 @@
   "revision": "unsloth",
   "target_modules": [
     "down_proj",
-    "v_proj",
     "o_proj",
-    "q_proj",
-    "gate_proj",
     "k_proj",
-    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "revision": "unsloth",
   "target_modules": [
     "down_proj",
     "o_proj",
     "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3a2b7faedb29f1c703b30daef8a903ffec26468657b368c3122b27fe64655d
-size 119597408

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ae4b4eb9e9cbc7b813538b07ae4f38f90359270161e133b87cbc24c7ceca749
+size 167832240

generation_config.json CHANGED Viewed

@@ -1,7 +1,9 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "pad_token_id": 32000,
   "transformers_version": "4.40.2"
 }

 {
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.40.2"
 }