Instructions to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF 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 pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF: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 pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF: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 pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pbatra/TinyLlama-1.1B-Chat-v1.0-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": "pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M

SGLang

How to use pbatra/TinyLlama-1.1B-Chat-v1.0-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 "pbatra/TinyLlama-1.1B-Chat-v1.0-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": "pbatra/TinyLlama-1.1B-Chat-v1.0-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 "pbatra/TinyLlama-1.1B-Chat-v1.0-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": "pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF with Ollama:
```
ollama run hf.co/pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF with Docker Model Runner:
```
docker model run hf.co/pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
```

Lemonade

How to use pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pbatra/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TinyLlama-1.1B-Chat-v1.0-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

pbatra commited on May 15, 2024

Commit

d6085e9

verified ·

1 Parent(s): 2e9967e

Update README.md

Browse files

Files changed (1) hide show

README.md +45 -13

README.md CHANGED Viewed

@@ -1,18 +1,50 @@
 # TinyLlama-1.1B-Chat-v1.0
 This repository contains quantized versions of the model from the original repository: [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
-| Name | Quantization Method | Size (MB) |
 |------|---------------------|-----------|
-| tinyllama-1.1b-chat-v1.0.Q2_K.gguf | q2_k | 412.11 |
-| tinyllama-1.1b-chat-v1.0.Q3_K_S.gguf | q3_k_s | 476.21 |
-| tinyllama-1.1b-chat-v1.0.Q3_K_M.gguf | q3_k_m | 523.00 |
-| tinyllama-1.1b-chat-v1.0.Q3_K_L.gguf | q3_k_l | 564.12 |
-| tinyllama-1.1b-chat-v1.0.Q4_0.gguf | q4_0 | 607.23 |
-| tinyllama-1.1b-chat-v1.0.Q4_K_S.gguf | q4_k_s | 610.23 |
-| tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf | q4_k_m | 636.88 |
-| tinyllama-1.1b-chat-v1.0.Q5_0.gguf | q5_0 | 730.54 |
-| tinyllama-1.1b-chat-v1.0.Q5_K_S.gguf | q5_k_s | 730.54 |
-| tinyllama-1.1b-chat-v1.0.Q5_K_M.gguf | q5_k_m | 745.82 |
-| tinyllama-1.1b-chat-v1.0.Q6_K.gguf | q6_k | 861.56 |
-| tinyllama-1.1b-chat-v1.0.Q8_0.gguf | q8_0 | 1115.62 |

+---
+base_model: "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+language:
+  - en
+tags:
+- transformers
+- safetensors
+- llama
+- text-generation
+- conversational
+- en
+- dataset:cerebras/SlimPajama-627B
+- dataset:bigcode/starcoderdata
+- dataset:HuggingFaceH4/ultrachat_200k
+- dataset:HuggingFaceH4/ultrafeedback_binarized
+- license:apache-2.0
+- autotrain_compatible
+- endpoints_compatible
+- text-generation-inference
+- region:us
+license: "apache-2.0"
+inference: false
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+quantized_by: pbatra
+---
 # TinyLlama-1.1B-Chat-v1.0
 This repository contains quantized versions of the model from the original repository: [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
+| Name | Quantization Method | Size (GB) |
 |------|---------------------|-----------|
+| tinyllama-1.1b-chat-v1.0.fp16.gguf | FP16 | 2.05 |
+| tinyllama-1.1b-chat-v1.0.fp32.gguf | FP32 | 4.10 |
+| tinyllama-1.1b-chat-v1.0.Q2_K.gguf | q2_k | 0.40 |
+| tinyllama-1.1b-chat-v1.0.Q3_K_S.gguf | q3_k_s | 0.47 |
+| tinyllama-1.1b-chat-v1.0.Q3_K_M.gguf | q3_k_m | 0.51 |
+| tinyllama-1.1b-chat-v1.0.Q3_K_L.gguf | q3_k_l | 0.55 |
+| tinyllama-1.1b-chat-v1.0.Q4_0.gguf | q4_0 | 0.59 |
+| tinyllama-1.1b-chat-v1.0.Q4_K_S.gguf | q4_k_s | 0.60 |
+| tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf | q4_k_m | 0.62 |
+| tinyllama-1.1b-chat-v1.0.Q5_0.gguf | q5_0 | 0.71 |
+| tinyllama-1.1b-chat-v1.0.Q5_K_S.gguf | q5_k_s | 0.71 |
+| tinyllama-1.1b-chat-v1.0.Q5_K_M.gguf | q5_k_m | 0.73 |
+| tinyllama-1.1b-chat-v1.0.Q6_K.gguf | q6_k | 0.84 |
+| tinyllama-1.1b-chat-v1.0.Q8_0.gguf | q8_0 | 1.09 |