Instructions to use smangrul/llama-3-8B-instruct-function-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smangrul/llama-3-8B-instruct-function-calling with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "smangrul/llama-3-8B-instruct-function-calling")

llama-cpp-python

How to use smangrul/llama-3-8B-instruct-function-calling with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="smangrul/llama-3-8B-instruct-function-calling",
	filename="llama-3-8B-instruct-function-calling-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use smangrul/llama-3-8B-instruct-function-calling with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smangrul/llama-3-8B-instruct-function-calling:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smangrul/llama-3-8B-instruct-function-calling:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smangrul/llama-3-8B-instruct-function-calling:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smangrul/llama-3-8B-instruct-function-calling:Q4_K_M

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 smangrul/llama-3-8B-instruct-function-calling:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf smangrul/llama-3-8B-instruct-function-calling:Q4_K_M

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 smangrul/llama-3-8B-instruct-function-calling:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smangrul/llama-3-8B-instruct-function-calling:Q4_K_M

Use Docker

docker model run hf.co/smangrul/llama-3-8B-instruct-function-calling:Q4_K_M

LM Studio
Jan
Ollama
How to use smangrul/llama-3-8B-instruct-function-calling with Ollama:
```
ollama run hf.co/smangrul/llama-3-8B-instruct-function-calling:Q4_K_M
```

Unsloth Studio

How to use smangrul/llama-3-8B-instruct-function-calling 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 smangrul/llama-3-8B-instruct-function-calling 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 smangrul/llama-3-8B-instruct-function-calling to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for smangrul/llama-3-8B-instruct-function-calling to start chatting

Atomic Chat new
Docker Model Runner
How to use smangrul/llama-3-8B-instruct-function-calling with Docker Model Runner:
```
docker model run hf.co/smangrul/llama-3-8B-instruct-function-calling:Q4_K_M
```

Lemonade

How to use smangrul/llama-3-8B-instruct-function-calling with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smangrul/llama-3-8B-instruct-function-calling:Q4_K_M

Run and chat with the model

lemonade run user.llama-3-8B-instruct-function-calling-Q4_K_M

List all available models

lemonade list

smangrul commited on Apr 21, 2024

Commit

e3bdfca

verified ·

1 Parent(s): d9388c5

Update tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +10 -9

tokenizer_config.json CHANGED Viewed

@@ -2079,15 +2079,16 @@
     "<pad>"
   ],
   "bos_token": "<|begin_of_text|>",
-  "chat_template":
-  {
-    "name": "default",
-    "template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% if loop.last and add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% endfor %}"
-  },
-  {
-    "name": "tool_use",
-    "template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% if loop.last and add_generation_prompt %}{{ '<|start_header_id|>' }}{% endif %}{% endfor %}"
-  },
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "model_input_names": [

     "<pad>"
   ],
   "bos_token": "<|begin_of_text|>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% if loop.last and add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% endfor %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% if loop.last and add_generation_prompt %}{{ '<|start_header_id|>' }}{% endif %}{% endfor %}"
+    }
+  ],
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "model_input_names": [