Who developed Llama 2 7B Chat Text2code and how large is it?

Llama 2 7B Chat Text2code is developed by SwastikM, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Llama 2 7B Chat Text2code?

Llama 2 7B Chat Text2code is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 2 7B Chat Text2code by SwastikM

Name: Llama 2 7B Chat Text2code
Author: SwastikM

Llama 2 7B Chat Text2code is an open-source language model by SwastikM. Features: 7b LLM, License: openrail, Quantized, LLM Explorer Score: 0.12.

Arxiv:2208.07339 Arxiv:2210.17323 Adapter Base model:adapter:thebloke/ll... Base model:thebloke/llama-2-7b... Co2 eq emissions Dataset:flytech/python-codes-2... En Finetuned Gptq Instruction2code Llama-2-7b-chat Lora Nl2code Peft Python Quantized Region:us Safetensors Text2code Text2python

Model Card on HF 🤗: https://huggingface.co/SwastikM/Llama-2-7B-Chat-text2code

Llama 2 7B Chat Text2code Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

research, personal projects

Applications:

text-to-code, nl2code, instruction2code

Primary Use Cases:

Generate Python code based on instructions

Additional Notes

Model trained using parameter efficient fine-tuning (PEFT) with LoRA on a 4bit quantized setup.

Supported Languages

en (English)

Training Details

Data Sources:

flytech/python-codes-25k

Data Volume:

20,000 samples

Methodology:

Finetuning with LoRA on a 4bit quantized model

Hardware Used:

1 P100 16GB GPU

LLM Name	Llama 2 7B Chat Text2code
Repository 🤗	https://huggingface.co/SwastikM/Llama-2-7B-Chat-text2code
Base Model(s)	TheBloke/Llama-2-7b-Chat-GPTQ TheBloke/Llama-2-7b-Chat-GPTQ
Model Size	7b
Required VRAM	0 GB
Updated	2026-07-14
Maintainer	SwastikM
Model Files	0.0 GB 0.1 GB 0.0 GB 0.0 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	Adapter
License	openrail
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|q_proj\|k_proj\|o_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	8

Rank the Llama 2 7B Chat Text2code capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Llama 2 7B Chat Text2code

Best Alternatives	Context / RAM	Downloads	Likes
Mistral Finetuned Bookcorpus	0K / 0 GB	5	0
Term Qwen2 7 Json Lora	0K / 0.1 GB	6	0
LMS Chatbot	0K / 0 GB	5	0
Zephyr 7B Alpha GPTQ	0K / 0 GB	2	1
Selfbot 256 Mistral	0K / 0.4 GB	6	0
Thesa	0K / 0 GB	4	1
Futadom Mistral	0K / 0.2 GB	7	1
Humiliation Mistral	0K / 0.2 GB	4	1
Gnosis Reformatted Mistral	0K / 0.2 GB	7	0
Zephyr Finetuned Legal	0K / 0 GB	2	1

Note: green Score (e.g. "73.2") means that the model is better than SwastikM/Llama-2-7B-Chat-text2code.