Instructions to use cstr/salamandra-7b-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cstr/salamandra-7b-instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="cstr/salamandra-7b-instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("cstr/salamandra-7b-instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cstr/salamandra-7b-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 cstr/salamandra-7b-instruct-GGUF:F32
# Run inference directly in the terminal:
llama cli -hf cstr/salamandra-7b-instruct-GGUF:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cstr/salamandra-7b-instruct-GGUF:F32
# Run inference directly in the terminal:
llama cli -hf cstr/salamandra-7b-instruct-GGUF:F32

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 cstr/salamandra-7b-instruct-GGUF:F32
# Run inference directly in the terminal:
./llama-cli -hf cstr/salamandra-7b-instruct-GGUF:F32

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 cstr/salamandra-7b-instruct-GGUF:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cstr/salamandra-7b-instruct-GGUF:F32

Use Docker

docker model run hf.co/cstr/salamandra-7b-instruct-GGUF:F32

LM Studio
Jan

vLLM

How to use cstr/salamandra-7b-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cstr/salamandra-7b-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": "cstr/salamandra-7b-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cstr/salamandra-7b-instruct-GGUF:F32

SGLang

How to use cstr/salamandra-7b-instruct-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 "cstr/salamandra-7b-instruct-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": "cstr/salamandra-7b-instruct-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 "cstr/salamandra-7b-instruct-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": "cstr/salamandra-7b-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use cstr/salamandra-7b-instruct-GGUF with Ollama:
```
ollama run hf.co/cstr/salamandra-7b-instruct-GGUF:F32
```

Unsloth Studio

How to use cstr/salamandra-7b-instruct-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 cstr/salamandra-7b-instruct-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 cstr/salamandra-7b-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cstr/salamandra-7b-instruct-GGUF to start chatting

Docker Model Runner
How to use cstr/salamandra-7b-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/cstr/salamandra-7b-instruct-GGUF:F32
```

Lemonade

How to use cstr/salamandra-7b-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cstr/salamandra-7b-instruct-GGUF:F32

Run and chat with the model

lemonade run user.salamandra-7b-instruct-GGUF-F32

List all available models

lemonade list

Atomic Chat

GGUF quants

Experimental GGUF quantization of BSC-LT/salamandra-7b-instruct from llama.cpp (older version b2750).

Use with common ChatLM template.

Below the start of the original Model Card, check it for more details.

Salamandra Model Card

Salamandra comes in three different sizes — 2B, 7B and 40B parameters — with their respective base and instruction-tuned variants. This model card corresponds to the 7B instructed version.

To visit the model cards of other Salamandra versions, please refer to the Model Index.

The entire Salamandra family is released under a permissive Apache 2.0 license. Along with the open weights, all training scripts and configuration files are made publicly available in this GitHub repository.

DISCLAIMER: This model is a first proof-of-concept designed to demonstrate the instruction-following capabilities of recently released base models. It has been optimized to engage in conversation but has NOT been aligned through RLHF to filter or avoid sensitive topics. As a result, it may generate harmful or inappropriate content. The team is actively working to enhance its performance through further instruction and alignment with RL techniques.

Provenance and EU AI Act Art. 53 note

Upstream model: BSC-LT/salamandra-7b-instruct — published by BSC-LT.
Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.

Downloads last month: 285

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

32-bit

Model tree for cstr/salamandra-7b-instruct-GGUF

Base model

BSC-LT/salamandra-7b

Finetuned

BSC-LT/salamandra-7b-instruct

Quantized

(16)

this model

cstr
/

salamandra-7b-instruct-GGUF

GGUF quants

Salamandra Model Card

Provenance and EU AI Act Art. 53 note

Model tree for cstr/salamandra-7b-instruct-GGUF

Space using cstr/salamandra-7b-instruct-GGUF 1