from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16")
model = AutoModelForCausalLM.from_pretrained("nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16")
import { pipeline } from '@huggingface/transformers';
const generator = await pipeline('text-generation', 'nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16');
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: "nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16",
Inputs: "Hello, I am a language model",
})
// Using HF candle crate
use candle_transformers::models::llama;
let api = Api::new()?;
let repo = api.model("nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16".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("nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16.gguf", model_params);
<?php
// Call HF Inference API for text generation
$ch = curl_init("https://api-inference.huggingface.co/models/nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16");
curl_setopt($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("nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1")
model = AutoModelForCausalLM.from_pretrained("nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1")
import { pipeline } from '@huggingface/transformers';
const generator = await pipeline('text-generation', 'nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1');
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/llama-3.2-nemoretriever-1b-vlm-embed-v1",
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/llama-3.2-nemoretriever-1b-vlm-embed-v1".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/llama-3.2-nemoretriever-1b-vlm-embed-v1.gguf", model_params);
<?php
// Call HF Inference API for text generation
$ch = curl_init("https://api-inference.huggingface.co/models/nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer HF_API_TOKEN"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["inputs" => "Hello, I am a language model"]));
