Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq

Model is very good put producing random gibberish code and the end

#4
by suraj007 - opened

@TheBloke model is good and tried many ways but not able to remove the gibberish code stuff generating after the answer. can you please do something to eliminate that issue. sample response from model iam providing below. you can see the code after answer its consistant i tried many prompt template still same

So the website is Discord (dis.org). <?php

namespace App\Http\Controllers;

use Illuminate\Http\Request;
use App\Models\User;
use App\Rules\MatchOldPassword;
use Illuminate\Support\Facades\Hash;
use Illuminate\Validation\ValidatesWhenResolving;

class ResetPasswordController extends Controller

same problem, i feel like there is something wrong with my webui configuration. You can prompt the model with "End your response with <|end_of_turn|>" as a quick-fix.

same problem, i feel like there is something wrong with my webui configuration. You can prompt the model with "End your response with <|end_of_turn|>" as a quick-fix.

<3 thanks

Sign up or log in to comment