Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Pongsaky

llama3.2-typhoon2-1b-instruct-untagged

This Pongsaky model is a 1.24B-parameter Llama text-generation fine-tune. Its card names an scb10x typhoon2 instruct source with Unsloth and TRL training under Apache-2.0.

Publisher
Pongsaky
Task
text-generation
Model type
llama
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

The model is published by Pongsaky as a text-generation fine-tune in the typhoon2 1B instruct line. The captured configuration identifies LlamaForCausalLM with a llama model type, and Safetensors metadata reports 1,235,974,144 parameters. According to the model card, it was fine-tuned from scb10x/llama3.2-typhoon2-1b-instruct using Unsloth with Hugging Face's TRL library.

Recorded capabilities

Documented typhoon2 source

According to the model card, the model was fine-tuned from scb10x/llama3.2-typhoon2-1b-instruct; hub tags separately record a typhoon-ai instruct base entry.

Unsloth and TRL stack

According to the card, training used Unsloth with Hugging Face's TRL library.

Llama 1.24B configuration

Captured config identifies LlamaForCausalLM and llama, with Safetensors metadata reporting 1,235,974,144 parameters.

Apache-2.0 record

The hub record and card both carry an Apache-2.0 license value.

Use cases in the source record

  • Conversational text generation using the record's transformers, conversational, and endpoints-compatible configuration.
  • Unsloth and TRL fine-tune study building on the documented typhoon2 instruct source model.

Limitations and unknowns

  • No evaluation results, context-window value, or dataset details were extracted.
  • The card and hub tags name different typhoon2 instruct publishers, so exact base lineage should be confirmed at the source.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Pongsaky/llama3.2-typhoon2-1b-instruct-untagged

Captured: Unknown. Processed: 2026-09-07T19:35:15.145954+00:00.

Uploaded model Developed by: Pongsaky License: apache-2.0 Finetuned from model : scb10x/llama3.2-typhoon2-1b-instruct This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

F001F002F003F004F005F006F007F008F009F010F011