LLM EXPLORER 61,491 MODELS INDEXED

StructLM 34B by TIGER-Lab

By TIGER-Lab · 9 downloads

StructLM 34B is an open-source language model by TIGER-Lab. Features: 34b LLM, VRAM: 67.6GB, Context: 16K, License: mit, Code Generating, LLM Explorer Score: 0.11.

  Arxiv:2402.16671   Codegen   Dataset:tiger-lab/skginstruct   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF πŸ€—: https://huggingface.co/TIGER-Lab/StructLM-34B 

StructLM 34B Parameters and Internals

Model Type 
language model, structured knowledge grounding
Use Cases 
Areas:
research
Applications:
interpretation of structured data
Limitations:
May lack performance for chat applications
Additional Notes 
The 13B model uses a different prompt format than the 7B model.
Supported Languages 
en (high)
Training Details 
Data Sources:
TIGER-Lab/SKGInstruct, Open-Orca/SlimOrca
Methodology:
Finetuned with CodeLlama-Instruct-hf as base models
Input Output 
Input Format:
Specified prompt format
Accepted Modalities:
text
Output Format:
Structured outputs as per task requirements
Performance Tips:
Refer to evaluation code and setup on GitHub
LLM NameStructLM 34B
Repository πŸ€—https://huggingface.co/TIGER-Lab/StructLM-34B 
Model Size34b
Required VRAM67.6 GB
Updated2026-07-23
MaintainerTIGER-Lab
Model Typellama
Model Files  5.0 GB: 1-of-14   4.9 GB: 2-of-14   4.8 GB: 3-of-14   4.9 GB: 4-of-14   4.8 GB: 5-of-14   4.9 GB: 6-of-14   4.8 GB: 7-of-14   4.9 GB: 8-of-14   4.8 GB: 9-of-14   4.9 GB: 10-of-14   4.8 GB: 11-of-14   4.9 GB: 12-of-14   4.8 GB: 13-of-14   4.4 GB: 14-of-14
Supported Languagesen
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.37.2
Tokenizer ClassCodeLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the StructLM 34B

Model
Likes
Downloads
VRAM
StructLM 34B GGUF219612 GB

Best Alternatives to StructLM 34B

Best Alternatives
Context / RAM
Downloads
Likes
...gpt 32K Codellama 34B Instruct32K / 67.5 GB562
CodeLlama 34B Instruct Hf16K / 67.5 GB22872304
CodeLlama 34B Instruct Hf16K / 1.4 GB53
CodeLlama 34B Instruct Hf16K / 1.4 GB73
ReflectionCoder CL 34B16K / 67.6 GB77350
Speechless Codellama 34B V2.016K / 67.5 GB9617
CodeLlama 34B Hf16K / 67.5 GB27673178
Phind CodeLlama 34B V216K / 67.5 GB618834
Phind CodeLlama 34B V116K / 67.5 GB165320
Phind CodeLlama 34B Python V116K / 67.5 GB180252
Note: green Score (e.g. "73.2") means that the model is better than TIGER-Lab/StructLM-34B.