Instructions to use QuantFactory/Calme-Instruct-Extended-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Calme-Instruct-Extended-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Calme-Instruct-Extended-GGUF",
	filename="Calme-Instruct-Extended.Q2_K.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 QuantFactory/Calme-Instruct-Extended-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Calme-Instruct-Extended-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 QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Calme-Instruct-Extended-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 QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/Calme-Instruct-Extended-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Calme-Instruct-Extended-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 QuantFactory/Calme-Instruct-Extended-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 QuantFactory/Calme-Instruct-Extended-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Calme-Instruct-Extended-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Calme-Instruct-Extended-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Calme-Instruct-Extended-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Calme-Instruct-Extended-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Calme-Instruct-Extended-GGUF-Q4_K_M

List all available models

lemonade list

aashish1904 commited on Jul 22, 2024

Commit

f14e432

verified ·

1 Parent(s): 277f01f

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +171 -0

README.md ADDED Viewed

	@@ -0,0 +1,171 @@

+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+---
+![](https://cdn.discordapp.com/attachments/791342238541152306/1264099835221381251/image.png?ex=669ca436&is=669b52b6&hm=129f56187c31e1ed22cbd1bcdbc677a2baeea5090761d2f1a458c8b1ec7cca4b&)
+# QuantFactory/Calme-Instruct-Extended-GGUF
+This is quantized version of [arcee-ai/Calme-Instruct-Extended](https://huggingface.co/arcee-ai/Calme-Instruct-Extended) created using llama.cpp
+# Original Model Card
+# Calme-Instruct-Extended
+Calme-Instruct-Extended is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
+## 🧩 Configuration
+```yaml
+  slices:
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 3
+          - 4
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 7
+          - 8
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 11
+          - 12
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 15
+          - 16
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 19
+          - 20
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 23
+          - 24
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 27
+          - 28
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
+        layer_range:
+          - 31
+          - 32
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  merge_method: passthrough
+  dtype: bfloat16
+```