Instructions to use tensorblock/Llama-68M-Chat-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/Llama-68M-Chat-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/Llama-68M-Chat-v1-GGUF",
	filename="Llama-68M-Chat-v1-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tensorblock/Llama-68M-Chat-v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

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 tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

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 tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/Llama-68M-Chat-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/Llama-68M-Chat-v1-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": "tensorblock/Llama-68M-Chat-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

Ollama
How to use tensorblock/Llama-68M-Chat-v1-GGUF with Ollama:
```
ollama run hf.co/tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/Llama-68M-Chat-v1-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 tensorblock/Llama-68M-Chat-v1-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 tensorblock/Llama-68M-Chat-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/Llama-68M-Chat-v1-GGUF to start chatting

Docker Model Runner
How to use tensorblock/Llama-68M-Chat-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K
```

Lemonade

How to use tensorblock/Llama-68M-Chat-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/Llama-68M-Chat-v1-GGUF:Q2_K

Run and chat with the model

lemonade run user.Llama-68M-Chat-v1-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Nov 16, 2024

Commit

9ff7d2e

verified ·

1 Parent(s): 4add9fd

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -12

README.md CHANGED Viewed

@@ -182,8 +182,16 @@ This repo contains GGUF format model files for [Felladrin/Llama-68M-Chat-v1](htt
 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
 ## Prompt template
 ```
 <|im_start|>system
 {system_prompt}<|im_end|>
@@ -196,18 +204,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
-| [Llama-68M-Chat-v1-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q2_K.gguf) | Q2_K | 0.033 GB | smallest, significant quality loss - not recommended for most purposes |
-| [Llama-68M-Chat-v1-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q3_K_S.gguf) | Q3_K_S | 0.037 GB | very small, high quality loss |
-| [Llama-68M-Chat-v1-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q3_K_M.gguf) | Q3_K_M | 0.038 GB | very small, high quality loss |
-| [Llama-68M-Chat-v1-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q3_K_L.gguf) | Q3_K_L | 0.039 GB | small, substantial quality loss |
-| [Llama-68M-Chat-v1-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q4_0.gguf) | Q4_0 | 0.042 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
-| [Llama-68M-Chat-v1-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q4_K_S.gguf) | Q4_K_S | 0.042 GB | small, greater quality loss |
-| [Llama-68M-Chat-v1-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q4_K_M.gguf) | Q4_K_M | 0.043 GB | medium, balanced quality - recommended |
-| [Llama-68M-Chat-v1-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q5_0.gguf) | Q5_0 | 0.047 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
-| [Llama-68M-Chat-v1-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q5_K_S.gguf) | Q5_K_S | 0.047 GB | large, low quality loss - recommended |
-| [Llama-68M-Chat-v1-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q5_K_M.gguf) | Q5_K_M | 0.048 GB | large, very low quality loss - recommended |
-| [Llama-68M-Chat-v1-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q6_K.gguf) | Q6_K | 0.053 GB | very large, extremely low quality loss |
-| [Llama-68M-Chat-v1-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/tree/main/Llama-68M-Chat-v1-Q8_0.gguf) | Q8_0 | 0.068 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction

 The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
 ## Prompt template
 ```
 <|im_start|>system
 {system_prompt}<|im_end|>
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
+| [Llama-68M-Chat-v1-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q2_K.gguf) | Q2_K | 0.033 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-68M-Chat-v1-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q3_K_S.gguf) | Q3_K_S | 0.037 GB | very small, high quality loss |
+| [Llama-68M-Chat-v1-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q3_K_M.gguf) | Q3_K_M | 0.038 GB | very small, high quality loss |
+| [Llama-68M-Chat-v1-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q3_K_L.gguf) | Q3_K_L | 0.039 GB | small, substantial quality loss |
+| [Llama-68M-Chat-v1-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q4_0.gguf) | Q4_0 | 0.042 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-68M-Chat-v1-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q4_K_S.gguf) | Q4_K_S | 0.042 GB | small, greater quality loss |
+| [Llama-68M-Chat-v1-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q4_K_M.gguf) | Q4_K_M | 0.043 GB | medium, balanced quality - recommended |
+| [Llama-68M-Chat-v1-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q5_0.gguf) | Q5_0 | 0.047 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-68M-Chat-v1-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q5_K_S.gguf) | Q5_K_S | 0.047 GB | large, low quality loss - recommended |
+| [Llama-68M-Chat-v1-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q5_K_M.gguf) | Q5_K_M | 0.048 GB | large, very low quality loss - recommended |
+| [Llama-68M-Chat-v1-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q6_K.gguf) | Q6_K | 0.053 GB | very large, extremely low quality loss |
+| [Llama-68M-Chat-v1-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-68M-Chat-v1-GGUF/blob/main/Llama-68M-Chat-v1-Q8_0.gguf) | Q8_0 | 0.068 GB | very large, extremely low quality loss - not recommended |
 ## Downloading instruction