Instructions to use s3dev-ai/Falcon3-10B-Instruct-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use s3dev-ai/Falcon3-10B-Instruct-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 s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf s3dev-ai/Falcon3-10B-Instruct-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 s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Use Docker

docker model run hf.co/s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use s3dev-ai/Falcon3-10B-Instruct-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "s3dev-ai/Falcon3-10B-Instruct-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": "s3dev-ai/Falcon3-10B-Instruct-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Ollama
How to use s3dev-ai/Falcon3-10B-Instruct-gguf with Ollama:
```
ollama run hf.co/s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M
```
Unsloth Desktop

How to use s3dev-ai/Falcon3-10B-Instruct-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use s3dev-ai/Falcon3-10B-Instruct-gguf with Docker Model Runner:
```
docker model run hf.co/s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M
```

Lemonade

How to use s3dev-ai/Falcon3-10B-Instruct-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Falcon3-10B-Instruct-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use s3dev-ai/Falcon3-10B-Instruct-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use s3dev-ai/Falcon3-10B-Instruct-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "s3dev-ai/Falcon3-10B-Instruct-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

s3dev-ai commited on Apr 20

Commit

ef4584b

verified ·

1 Parent(s): e404335

Upload folder using huggingface_hub

Browse files

Files changed (18) hide show

.gitattributes +6 -0
Falcon3-10B-Instruct-BF16.gguf +3 -0
Falcon3-10B-Instruct-Q2_K.gguf +3 -0
Falcon3-10B-Instruct-Q4_K_M.gguf +3 -0
Falcon3-10B-Instruct-Q5_K_M.gguf +3 -0
Falcon3-10B-Instruct-Q6_K.gguf +3 -0
Falcon3-10B-Instruct-Q8_0.gguf +3 -0
README.md +77 -0
imgs/falcon3-10b-kde.png +0 -0
imgs/falcon3-10b-mean.png +0 -0
imgs/falcon3-10b-range.png +0 -0
imgs/falcon3-10b-stddev.png +0 -0
sha256/Falcon3-10B-Instruct-BF16.sha256 +1 -0
sha256/Falcon3-10B-Instruct-Q2_K.sha256 +1 -0
sha256/Falcon3-10B-Instruct-Q4_K_M.sha256 +1 -0
sha256/Falcon3-10B-Instruct-Q5_K_M.sha256 +1 -0
sha256/Falcon3-10B-Instruct-Q6_K.sha256 +1 -0
sha256/Falcon3-10B-Instruct-Q8_0.sha256 +1 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Falcon3-10B-Instruct-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Falcon3-10B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Falcon3-10B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Falcon3-10B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Falcon3-10B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Falcon3-10B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Falcon3-10B-Instruct-BF16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6220c171d8e529be1530b5a1662729bea4ed1d496f61e7b7852d165390e79e81
+size 20616558208

Falcon3-10B-Instruct-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd22e7e42323da970455ab451e5731cc6f43ac45e204fe7289e473f35f7cf31
+size 3924047488

Falcon3-10B-Instruct-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a8f9e588298d8fbfaca924f348c50918fe891a23a223c08b9d9edaf7a3cb0c
+size 6287521408

Falcon3-10B-Instruct-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08608a7d6d2e08d86484901a222f50b4f732a833fd27e9d69d430e7f9e4d7261
+size 7340553856

Falcon3-10B-Instruct-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa6cc4bd124524ccf3e74613e27679c2cf90fced1bec79a6535d5c9ea452b1e
+size 8459400832

Falcon3-10B-Instruct-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:001a07baaaffec0ae8086a12564e46506ec2d550ef2277191b2a70a31136fd93
+size 10955241088

README.md ADDED Viewed

	@@ -0,0 +1,77 @@

+---
+base_model:
+  - tiiuae/Falcon3-10B-Instruct
+language:
+  - en
+model_creator: tiiuae
+model_name: tiiuae/Falcon3-10B-Instruct
+model_type: llama
+quantized_by: s3dev-ai
+tags:
+  - text-generation
+---
+# Overview
+This model repository provides various quantisations of the following [base model](https://huggingface.co/tiiuae/Falcon3-10B-Instruct), in GGUF format.
+- tiiuae/Falcon3-10B-Instruct
+# Model Description
+For a full model description, please refer to the [base model's](https://huggingface.co/tiiuae/Falcon3-10B-Instruct) card.
+This model, and subsequent quantisations, have been converted directly from the author's base model *unaltered*.
+## How are the GGUF files created?
+After cloning the author's original base model repository, [`llama.cpp`](https://github.com/ggml-org/llama.cpp) is used to convert the model to GGUF format, using `--outtype=bf16` to preserve the original model's 16-bit fidelity.
+Finally, for each subsequent quantisation level, `llama.cpp`'s `llama-quantize` executable is called using the BF16 GGUF file as the source file.
+# Quantisation
+The purpose of this repository is to provide *unaltered*  quantisations of the author's base model. This section is designed to help the user visualise the difference in quantisation levels, in efforts to assist in model (quantisation) selection.
+## Comparison Statistics
+To aid a user in model/quantisation selection, the team has created the following statistics specifically for comparing the similarity scores across quantisation runs.
+The dataset against which each run was conducted is composed of 175 question/answer pairs, divided amongst 7 topics, specifically designed to test a quantisation's processing ability. The test dataset was created by Mistral Large (via [Le Chat](https://chat.mistral.ai/chat)) using prompts explicitly stating the requirement for the question/answer pairs to be designed for Mistral model quantisation testing.
+The similarity scores used by these statistics were calculated as the cosine similarity between the embedding of the 'gold standard' answer provided in the dataset, and the embedding of the response from the quantised model. The embedding model used in these tests is the [all-MiniLM-L6-v2 Q8_0](https://huggingface.co/s3dev-ai/all-MiniLM-L6-v2-gguf).
+### Range
+The range graph below illustrates how the range of similarity scores varies amongst the quantisation levels. Included in the range stats are the:
+- Minimum scores
+- Maximum scores
+- Mean scores
+- Score distribution (KDE)
+- Outliers
+<!-- Range image -->
+<div align="center">
+  <img src="imgs/falcon3-10b-range.png" alt="Stats Graph: Range" width="90%">
+</div>
+### Mean
+The mean graph below illustrates how the mean similarity scores (when grouped by 'topic') vary amongst the quantisation levels.
+<!-- Mean image -->
+<div align="center">
+  <img src="imgs/falcon3-10b-mean.png" alt="Stats Graph: Mean" width="90%">
+</div>
+### Standard Deviation
+The standard deviation graph below illustrates the how spread of similarity scores vary amongst the quantisation levels, when grouped by the test dataset's 'topic' categories.
+<!-- StdDev image -->
+<div align="center">
+  <img src="imgs/falcon3-10b-stddev.png" alt="Stats Graph: StdDev" width="90%">
+</div>
+### Kernel Density Estimate
+The KDE graph below illustrates the how distribution of similarity scores vary amongst the quantisation levels.
+<!-- KDE image -->
+<div align="center">
+  <img src="imgs/falcon3-10b-kde.png" alt="Stats Graph: KDE" width="90%">
+</div>

imgs/falcon3-10b-kde.png ADDED Viewed

imgs/falcon3-10b-mean.png ADDED Viewed

imgs/falcon3-10b-range.png ADDED Viewed

imgs/falcon3-10b-stddev.png ADDED Viewed

sha256/Falcon3-10B-Instruct-BF16.sha256 ADDED Viewed

	@@ -0,0 +1 @@


1	+ 6220c171d8e529be1530b5a1662729bea4ed1d496f61e7b7852d165390e79e81 Falcon3-10B-Instruct-BF16.gguf

sha256/Falcon3-10B-Instruct-Q2_K.sha256 ADDED Viewed

	@@ -0,0 +1 @@


1	+ bbd22e7e42323da970455ab451e5731cc6f43ac45e204fe7289e473f35f7cf31 Falcon3-10B-Instruct-Q2_K.gguf

sha256/Falcon3-10B-Instruct-Q4_K_M.sha256 ADDED Viewed

	@@ -0,0 +1 @@


1	+ b6a8f9e588298d8fbfaca924f348c50918fe891a23a223c08b9d9edaf7a3cb0c Falcon3-10B-Instruct-Q4_K_M.gguf

sha256/Falcon3-10B-Instruct-Q5_K_M.sha256 ADDED Viewed

	@@ -0,0 +1 @@


1	+ 08608a7d6d2e08d86484901a222f50b4f732a833fd27e9d69d430e7f9e4d7261 Falcon3-10B-Instruct-Q5_K_M.gguf

sha256/Falcon3-10B-Instruct-Q6_K.sha256 ADDED Viewed

	@@ -0,0 +1 @@


1	+ 5aa6cc4bd124524ccf3e74613e27679c2cf90fced1bec79a6535d5c9ea452b1e Falcon3-10B-Instruct-Q6_K.gguf

sha256/Falcon3-10B-Instruct-Q8_0.sha256 ADDED Viewed

	@@ -0,0 +1 @@


1	+ 001a07baaaffec0ae8086a12564e46506ec2d550ef2277191b2a70a31136fd93 Falcon3-10B-Instruct-Q8_0.gguf