Instructions to use robbiemu/salamandra-2b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use robbiemu/salamandra-2b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="robbiemu/salamandra-2b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("robbiemu/salamandra-2b-instruct")
model = AutoModelForCausalLM.from_pretrained("robbiemu/salamandra-2b-instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use robbiemu/salamandra-2b-instruct 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 robbiemu/salamandra-2b-instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf robbiemu/salamandra-2b-instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf robbiemu/salamandra-2b-instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf robbiemu/salamandra-2b-instruct: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 robbiemu/salamandra-2b-instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf robbiemu/salamandra-2b-instruct:Q4_K_M

Use Docker

docker model run hf.co/robbiemu/salamandra-2b-instruct:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use robbiemu/salamandra-2b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "robbiemu/salamandra-2b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "robbiemu/salamandra-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/robbiemu/salamandra-2b-instruct:Q4_K_M

SGLang

How to use robbiemu/salamandra-2b-instruct 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 "robbiemu/salamandra-2b-instruct" \
    --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": "robbiemu/salamandra-2b-instruct",
		"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 "robbiemu/salamandra-2b-instruct" \
        --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": "robbiemu/salamandra-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use robbiemu/salamandra-2b-instruct with Ollama:
```
ollama run hf.co/robbiemu/salamandra-2b-instruct:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use robbiemu/salamandra-2b-instruct with Docker Model Runner:
```
docker model run hf.co/robbiemu/salamandra-2b-instruct:Q4_K_M
```

Lemonade

How to use robbiemu/salamandra-2b-instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull robbiemu/salamandra-2b-instruct:Q4_K_M

Run and chat with the model

lemonade run user.salamandra-2b-instruct-Q4_K_M

List all available models

lemonade list

Atomic Chat

gonzalez-agirre commited on Oct 1, 2024

Commit

bdc4a9f

1 Parent(s): bae5ed5

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -51,7 +51,7 @@ This model card corresponds to the 2B instructed version.
 To visit the model cards of other Salamandra versions, please refer to the [Model Index](#model-index).
 The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)).
-Along with the open weights, all training scripts and configuration files are made publicly available in [this GitHub repository](https://github.com/projecte-aina/salamandra).
 > [!WARNING]
 > **DISCLAIMER:** This model is a first proof-of-concept designed to demonstrate the instruction-following capabilities of recently released base models.
@@ -70,7 +70,7 @@ The pre-training corpus contains text in 35 European languages and code.
 ### Hyperparameters
-The full list of hyperparameters for each model can be found [here](https://github.com/projecte-aina/salamandra/tree/main/configs).
 ### Architecture
@@ -156,7 +156,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import transformers
 import torch
-model_id = "projecte-aina/salamandra-2b-instruct"
 text = "At what temperature does water boil?"
@@ -678,6 +678,6 @@ Technical report and paper coming soon.
 ## Model Index
 |Model|Base|Instruct|
 |:---:|:---:|:---:|
-|2B| [Link](https://huggingface.co/projecte-aina/salamandra-2b) | [Link](https://huggingface.co/projecte-aina/salamandra-2b-instruct) |
-|7B| [Link](https://huggingface.co/projecte-aina/salamandra-7b) | [Link](https://huggingface.co/projecte-aina/salamandra-7b-instruct) |
 |40B| WiP | WiP |

 To visit the model cards of other Salamandra versions, please refer to the [Model Index](#model-index).
 The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)).
+Along with the open weights, all training scripts and configuration files are made publicly available in [this GitHub repository](https://github.com/langtech-bsc/salamandra).
 > [!WARNING]
 > **DISCLAIMER:** This model is a first proof-of-concept designed to demonstrate the instruction-following capabilities of recently released base models.
 ### Hyperparameters
+The full list of hyperparameters for each model can be found [here](https://github.com/langtech-bsc/salamandra/tree/main/configs).
 ### Architecture
 import transformers
 import torch
+model_id = "BSC-LT/salamandra-2b-instruct"
 text = "At what temperature does water boil?"
 ## Model Index
 |Model|Base|Instruct|
 |:---:|:---:|:---:|
+|2B| [Link](https://huggingface.co/BSC-LT/salamandra-2b) | [Link](https://huggingface.co/BSC-LT/salamandra-2b-instruct) |
+|7B| [Link](https://huggingface.co/BSC-LT/salamandra-7b) | [Link](https://huggingface.co/BSC-LT/salamandra-7b-instruct) |
 |40B| WiP | WiP |