xgen-small-4B-instruct-r

Name: xgen-small-4B-instruct-r
Author: Salesforce

404

1 language

llama

Salesforce

Language Model

OTHER

4B params

New

404 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

9GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

4GB+ RAM

Code Examples

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Usagepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-instruct-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

generated = model.generate(inputs, max_new_tokens=128)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.