Instructions to use llmware/tiny-llama-chat-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/tiny-llama-chat-gguf with Transformers:

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

pipe = pipeline("text-generation", model="llmware/tiny-llama-chat-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/tiny-llama-chat-gguf")
model = AutoModelForCausalLM.from_pretrained("llmware/tiny-llama-chat-gguf")

llama-cpp-python

How to use llmware/tiny-llama-chat-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/tiny-llama-chat-gguf",
	filename="tiny-llama-chat.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use llmware/tiny-llama-chat-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/tiny-llama-chat-gguf
# Run inference directly in the terminal:
llama-cli -hf llmware/tiny-llama-chat-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/tiny-llama-chat-gguf
# Run inference directly in the terminal:
llama-cli -hf llmware/tiny-llama-chat-gguf

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 llmware/tiny-llama-chat-gguf
# Run inference directly in the terminal:
./llama-cli -hf llmware/tiny-llama-chat-gguf

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 llmware/tiny-llama-chat-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/tiny-llama-chat-gguf

Use Docker

docker model run hf.co/llmware/tiny-llama-chat-gguf

LM Studio
Jan

vLLM

How to use llmware/tiny-llama-chat-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/tiny-llama-chat-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/tiny-llama-chat-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmware/tiny-llama-chat-gguf

SGLang

How to use llmware/tiny-llama-chat-gguf 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 "llmware/tiny-llama-chat-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/tiny-llama-chat-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "llmware/tiny-llama-chat-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/tiny-llama-chat-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use llmware/tiny-llama-chat-gguf with Ollama:
```
ollama run hf.co/llmware/tiny-llama-chat-gguf
```

Unsloth Studio

How to use llmware/tiny-llama-chat-gguf 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 llmware/tiny-llama-chat-gguf 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 llmware/tiny-llama-chat-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/tiny-llama-chat-gguf to start chatting

Docker Model Runner
How to use llmware/tiny-llama-chat-gguf with Docker Model Runner:
```
docker model run hf.co/llmware/tiny-llama-chat-gguf
```

Lemonade

How to use llmware/tiny-llama-chat-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/tiny-llama-chat-gguf

Run and chat with the model

lemonade run user.tiny-llama-chat-gguf-{{QUANT_TAG}}

List all available models

lemonade list

doberst commited on Feb 8, 2025

Commit

1836906

verified ·

1 Parent(s): cea0db9

Upload 4 files

Browse files

Files changed (3) hide show

README.md +41 -3
config.json +4 -2
hash_record_sha256.json +4 -0

README.md CHANGED Viewed

@@ -1,3 +1,41 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+inference: false
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+base_model_relation: quantized
+tags:
+- green
+- llmware-chat
+- p1
+- gguf
+- emerald
+---
+# tiny-llama-chat-gguf
+**tiny-llama-chat-gguf** is an GGUF Q4_K_M int4 quantized version of TinyLlama-Chat, providing a very fast, very small inference implementation, optimized for AI PCs.
+[**tiny-llama-chat**](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) is the official chat finetuned version of tiny-llama.
+### Model Description
+- **Developed by:** TinyLlama
+- **Quantized by:** llmware
+- **Model type:** llama
+- **Parameters:** 1.1 billion
+- **Model Parent:** TinyLlama-1.1B-Chat-v1.0
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Uses:** Chat and general purpose LLM
+- **RAG Benchmark Accuracy Score:** NA
+- **Quantization:** int4
+## Model Card Contact
+[llmware on github](https://www.github.com/llmware-ai/llmware)
+[llmware on hf](https://www.huggingface.co/llmware)
+[llmware website](https://www.llmware.ai)

config.json CHANGED Viewed

@@ -1,8 +1,10 @@
 {
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -10,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
@@ -19,8 +22,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.0",
   "use_cache": true,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "tiny-llama-chat-gguf",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 32000
 }

hash_record_sha256.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+ "tiny-llama-chat.gguf": "1f7b92940e5711806cf4ea62a4ae588261ffb29f05e77f6dec282ac1ac41fdca",
+ "time_stamp": "2025-02-08_151503"
+}