LLM EXPLORER 61,561 MODELS INDEXED

Speechless Tora Code 7B V1.0 GPTQ by TheBloke

By TheBloke · 9 downloads
HF Repo ↗ Copy URL

Speechless Tora Code 7B V1.0 GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 3.9GB, Context: 16K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.09.

  4-bit Base model:quantized:uukuguy/s... Base model:uukuguy/speechless-...   Code Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-2....   Dataset:open-orca/openorca Dataset:tokenbender/python eva... Dataset:wizardlm/wizardlm evol...   En   Gptq   Instruct   Llama   Llama2   Model-index   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/speechless-tora-code-7B-v1.0-GPTQ 

Speechless Tora Code 7B V1.0 GPTQ Parameters and Internals

Model Type 
text-generation
Additional Notes 
A GPTQ-quantized model with various configurations for optimizing performance on different hardware setups.
Supported Languages 
en (English)
Training Details 
Data Sources:
jondurbin/airoboros-2.2, Open-Orca/OpenOrca, garage-bAInd/Open-Platypus, WizardLM/WizardLM_evol_instruct_V2_196k, TokenBender/python_eval_instruct_51k
Methodology:
fine-tuning with GPTQ
Context Length:
8192
Training Time:
19:24:49.43
Hardware Used:
A800-80G x 2
Model Architecture:
LLM architecture optimized for text generation
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
LLM NameSpeechless Tora Code 7B V1.0 GPTQ
Repository 🤗https://huggingface.co/TheBloke/speechless-tora-code-7B-v1.0-GPTQ 
Model NameSpeechless Tora Code 7B v1.0
Model CreatorJiangwen Su
Base Model(s)  uukuguy/speechless-tora-code-7b-v1.0   uukuguy/speechless-tora-code-7b-v1.0
Model Size7b
Required VRAM3.9 GB
Updated2026-08-07
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  3.9 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to Speechless Tora Code 7B V1.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB4927
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB60
CodeLlama 7B Instruct GPTQ16K / 3.9 GB49946
CausalLM 7B GPTQ8K / 5.9 GB75
Leo Hessianai 7B Chat GPTQ8K / 3.9 GB180
...ssianai 7B Chat Bilingual GPTQ8K / 3.9 GB60
Xgen 7B 8K Open Instruct Gptq8K / 4.2 GB54
Deepseek Math 7B Instruct GPTQ4K / 4.8 GB50
... Llama 2 7B Fast Instruct GPTQ4K / 4.1 GB953
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/speechless-tora-code-7B-v1.0-GPTQ.