ModelPrésentéExterne

DCL Qwen3 4B Instruct 2507 LoRA

The LoRA adapter (r=16, α=32, attention+MLP targets) behind DCL-Qwen3-4B-Instruct-2507, a fine-tune of Qwen/Qwen3-4B-Instruct-2507 that authors and repairs DCL (Russell East's Declarative Capability Language). See...

Sourcehuggingface.co/RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA/tree/622c6d7d409d4cb9ca73408c440ecd244e196114

TypeOtherModèle de baseQwen/Qwen3-4B-Instruct-2507VersionRevision 622c6d7BClasse

Source du modèle

Type: Other
Taille du fichier: 126 MB
Modèle de base: Qwen/Qwen3-4B-Instruct-2507
Version: vRevision 622c6d7
Mis à jour: 20 oct. 2026
Téléchargements: 13
Source: Hugging Face

Description de la source

DCL-Qwen3-4B-Instruct-2507 — LoRA adapter (~132 MB)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

m = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507",
                                         dtype=torch.bfloat16, device_map="auto")
m = PeftModel.from_pretrained(m, "RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")

Note: the adapter was trained against the 4-bit quantised base (QLoRA); applied to the full-precision base as above, behaviour matches the released merged model to within quantisation noise — the frozen-exam receipts were graded on the merged Q4_K_M build.

Trained on a private corpus of 507 compiler-verified, fully synthetic rows with Unsloth + TRL (PEFT 0.19.1) — kept private to protect the integrity of the frozen evaluation exam. Apache-2.0; base LICENSE retained.

Sources

1 source

Hugging FacePrincipalVersion 622c6d7d409d4cb9ca73408c440ecd244e196114

huggingface.co/RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA/tree/622c6d7d409d4cb9ca73408c440ecd244e196114

Vérifié 20 oct.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 126 MB · SHA-256 152f629b4974…0093 · Hugging Face

Download file

Extraits de sources

3 extraits

Readme3 aoûthuggingface.co/RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA

--- license: apache-2.0 base_model: Qwen/Qwen3-4B-Instruct-2507 pipeline_tag: text-generation library_name: peft language: - en tags: - dcl - capability-language - lora - qlora --- # DCL-Qwen3-4B-Instruct-2507 — LoRA adapter (~132 MB) The LoRA adapter (r=16, α=32, attention+MLP targets) behind [DCL-Qwen3-4B-Instruct-2507](https://huggingface.co/RichWoollcott/DCL-Qwen3-4B-Instruct-2507), a fine-tune of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) that authors and repairs [DCL](https://github.com/russelleast/Capability-Language) (Russell East's Declarative Capability Language). See the main model card for the evaluation table, the required serving prompt, and limitations. ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel import torch m = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507", dtype=torch.bfloat16, device_map="auto") m = PeftModel.from_pretrained(m, "RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA") tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507") ``` Note: the adapter was trained against the 4-bit quantised base (QLoRA); applied to the full-precision base as above, behaviour matches the released merged model to within quantisation noise — the frozen-exam receipts were graded on the merged Q4_K_M build. Trained on a private corpus of 507 compiler-verified, fully synthetic rows with Unsloth + TRL (PEFT 0.19.1) — kept private to protect the integrity of the frozen evaluation exam. Apache-2.0; base LICENSE retained.

Note20 oct.huggingface.co/RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA

Source context: 13 downloads · 0 likes · Pipeline text-generation · Library peft · Repo RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA

Note3 aoûthuggingface.co/RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA

Source context: 30 downloads · 0 likes · Pipeline text-generation · Library peft · Repo RichWoollcott/DCL-Qwen3-4B-Instruct-2507-LoRA