from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("nvidia/nemoretriever-parse")
model = AutoModelForCausalLM.from_pretrained("nvidia/nemoretriever-parse")
import { pipeline } from '@huggingface/transformers';
const generator = await pipeline('text-generation', 'nvidia/nemoretriever-parse');
const output = await generator('Hello, I am a language model', { max_new_tokens: 50 });
// Using Hugging Face Inference API
import "github.com/hupe1980/go-huggingface"
client := huggingface.NewInferenceClient("HF_API_TOKEN")
ic, err := client.TextGeneration(context.Background(), &huggingface.TextGenerationRequest{
Model: "nvidia/nemoretriever-parse",
Inputs: "Hello, I am a language model",
})
// Using HF candle crate
use candle_transformers::models::llama;
let api = Api::new()?;
let repo = api.model("nvidia/nemoretriever-parse".to_string());
// Load model using llama.cpp
#include "llama.h"
llama_model_params model_params = llama_model_default_params();
llama_model* model = llama_model_load_from_file("nvidia/nemoretriever-parse.gguf", model_params);
<?php
// Call HF Inference API for text generation
$ch = curl_init("https://api-inference.huggingface.co/models/nvidia/nemoretriever-parse");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer HF_API_TOKEN"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["inputs" => "Hello, I am a language model"]));
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B-Base")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B-Base")
import { pipeline } from '@huggingface/transformers';
const generator = await pipeline('text-generation', 'Qwen/Qwen3-0.6B-Base');
const output = await generator('Hello, I am a language model', { max_new_tokens: 50 });
// Using Hugging Face Inference API
import "github.com/hupe1980/go-huggingface"
client := huggingface.NewInferenceClient("HF_API_TOKEN")
ic, err := client.TextGeneration(context.Background(), &huggingface.TextGenerationRequest{
Model: "Qwen/Qwen3-0.6B-Base",
Inputs: "Hello, I am a language model",
})
// Using HF candle crate
use candle_transformers::models::llama;
let api = Api::new()?;
let repo = api.model("Qwen/Qwen3-0.6B-Base".to_string());
// Load model using llama.cpp
#include "llama.h"
llama_model_params model_params = llama_model_default_params();
llama_model* model = llama_model_load_from_file("Qwen/Qwen3-0.6B-Base.gguf", model_params);
<?php
// Call HF Inference API for text generation
$ch = curl_init("https://api-inference.huggingface.co/models/Qwen/Qwen3-0.6B-Base");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer HF_API_TOKEN"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["inputs" => "Hello, I am a language model"]));
