Instructions to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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": "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

Ollama
How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF with Ollama:
```
ollama run hf.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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": "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF with Docker Model Runner:
```
docker model run hf.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
```

Lemonade

How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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 "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-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"

FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF

GGUF quantizations of a LoRA fine-tune of microsoft/FastContext-1.0-4B-SFT (no longer available on the Hub), supervised fine-tuned on Salesforce/xlam-function-calling-60k.

Quantized from ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth. See that repository for the full-precision weights.


Base model	`microsoft/FastContext-1.0-4B-SFT` (no longer available on the Hub)
Training data	`Salesforce/xlam-function-calling-60k`
Method	LoRA supervised fine-tuning via Unsloth + TRL

Available quantizations

File	Size
`fastcontext-4b-sft_base-function-calling-xlam-unsloth.q2_k.gguf`	1.67 GB
`fastcontext-4b-sft_base-function-calling-xlam-unsloth.q3_k_m.gguf`	2.08 GB
`fastcontext-4b-sft_base-function-calling-xlam-unsloth.q4_k_m.gguf`	2.50 GB
`fastcontext-4b-sft_base-function-calling-xlam-unsloth.q5_k_m.gguf`	2.89 GB
`fastcontext-4b-sft_base-function-calling-xlam-unsloth.q6_k.gguf`	3.31 GB
`fastcontext-4b-sft_base-function-calling-xlam-unsloth.q8_0.gguf`	4.28 GB

Usage

llama.cpp

huggingface-cli download ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF fastcontext-4b-sft_base-function-calling-xlam-unsloth.q4_k_m.gguf --local-dir .
llama-cli -m fastcontext-4b-sft_base-function-calling-xlam-unsloth.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256

Ollama

echo 'FROM ./fastcontext-4b-sft_base-function-calling-xlam-unsloth.q4_k_m.gguf' > Modelfile
ollama create fastcontext-4b-sft_base-function-calling-xlam-unsloth-gguf -f Modelfile
ollama run fastcontext-4b-sft_base-function-calling-xlam-unsloth-gguf

Training configuration

Setting	Value
LoRA rank (r)	16
LoRA alpha	16
Learning rate	0.0002
Epochs	1
Effective batch size	8 (2 x 4 grad accum)
Max sequence length	2048
Base precision	4-bit (QLoRA)
Target modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`

Observed training loss

Measured from our SLURM logs for this configuration. These are training-loss observations only — no downstream benchmark evaluation has been run on this model, so they should not be read as a quality claim.

SLURM job	Steps	First loss	Final loss
`53225528`	94,254	1.1628	0.8690
`45169148`	7,500	0.6742	0.1443

Limitations

No benchmark evaluation has been run on this checkpoint. The only reported numbers are training-loss observations.
Inherits the biases, knowledge cutoff and failure modes of the base model.
Fine-tuned on a single instruction-following dataset; behaviour outside that distribution is untested.
LoRA adapters were merged into the base weights, so the merged model cannot be detached from this fine-tune.

Reproducing

Trained by notebooks/xlam_function_calling_fastcontext-4b-sft_unsloth.ipynb, executed non-interactively with papermill on a SLURM H100 partition (Unsloth + TRL, LoRA).

Card generated from the training run's own configuration and logs by scripts/generate_hub_model_card.py.

Downloads last month: 400

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF

Base model

microsoft/FastContext-1.0-4B-SFT

Adapter

(8)

this model

ermiaazarkhalili
/

FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF

FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF

Available quantizations

Usage

llama.cpp

Ollama

Training configuration

Observed training loss

Limitations

Reproducing

Model tree for ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF

Dataset used to train ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF