Qwen (Ben) Franklin

A local model zoo of custom Benjamin Franklin LoRA adapters trained on Qwen-family bases. These models explore a living, useful Franklin voice: printerly wit, civic practicality, identity persistence, English-only dialogue, tool-call cleanup, factual biography repair, and more coherent conversation.

22 custom Franklin adapters copied23.96 GB adapter artifactsRTX 3070 8GB tested

About

“Qwen (Ben) Franklin” is a set of local LoRA experiments that turn compact Qwen-family models into a Benjamin Franklin conversational persona. The adapters range from fast 1.7B prototypes through 4B cleanup/factual variants to the newer 7B Qwen2.5 experiments, which are the largest Franklin LoRAs proven trainable on this machine.

The key lesson: the 7B models feel more coherent, but stubborn factual corrections such as the Craven Street bones story still benefit from retrieval or prompt-context. Some 4B variants contain stronger factual phrasing but suffer offline tool_call-tag regressions.

Performance table

ModelBase familyGBrScoreFlagsCard
qwen2.5-7b-ben-franklin-v1-lite-r4-qvQwen2.5 7B Instruct 4-bit0.06430{'base_identity_leak': 1, 'overdenial': 1}card
qwen2.5-7b-ben-franklin-v2-coherence-r4-qvQwen2.5 7B Instruct 4-bit0.06433{'base_identity_leak': 1}card
qwen2.5-7b-ben-franklin-v3-factual-coherence-r4-qvQwen2.5 7B Instruct 4-bit0.06435{'base_identity_leak': 1}card
qwen2.5-7b-ben-franklin-v3c-factual-r8-qv-from-baseQwen2.5 7B Instruct 4-bit0.08828{'base_identity_leak': 1, 'overdenial': 1}card
qwen3-4b-instruct-2507-ben-franklin-v1-loraQwen3 4B Instruct 4-bit1.3416card
qwen3-4b-instruct-2507-ben-franklin-v2-chatml-loraQwen3 4B Instruct 4-bit2.1932card
qwen3-4b-instruct-2507-ben-franklin-v3-chatml-completions-loraQwen3 4B Instruct 4-bit2.1932card
qwen3-4b-instruct-2507-ben-franklin-v4-toolcall-clean-loraQwen3 4B Instruct 4-bit1.8132card
qwen3-4b-instruct-2507-ben-franklin-v5-english-lock-loraQwen3 4B Instruct 4-bit1.8132-92{'tool_call': 15, 'continuity_miss': 1}card
qwen3-1.7b-ben-franklin-identity-reinforced-loraQwen3 1.7B 4-bit0.9932card
qwen3-1.7b-ben-franklin-openai-expanded-loraQwen3 1.7B 4-bit1.232card
qwen3-1.7b-ben-franklin-thinking-loraQwen3 1.7B 4-bit0.9932card
qwen3-1.7b-ben-franklin-thinking-v2-loraQwen3 1.7B 4-bit0.7832card
qwen3-1.7b-ben-franklin-thinking-v3-negative-identity-loraQwen3 1.7B 4-bit0.7832card
qwen3-1.7b-ben-franklin-thinking-v4-balanced-loraQwen3 1.7B 4-bit0.7832card
qwen3-1.7b-ben-franklin-thinking-v5-ood-fixed-loraQwen3 1.7B 4-bit0.7832card
qwen3-1.7b-ben-franklin-thinking-v6-1-ood-fixed-loraQwen3 1.7B 4-bit0.9932card
qwen3-1.7b-ben-franklin-thinking-v6-contrastive-loraQwen3 1.7B 4-bit1.6232card
qwen3-1.7b-ben-franklin-thinking-v7-natural-dialogue-loraQwen3 1.7B 4-bit1.232card
qwen3-1.7b-ben-franklin-thinking-v8-minimal-thought-loraQwen3 1.7B 4-bit0.9932card
qwen3-1.7b-ben-franklin-thinking-v9-factual-dialogue-loraQwen3 1.7B 4-bit1.6232card
qwen3-1.7b-ben-franklin-thinking-v9-from-v2-factual-dialogue-loraQwen3 1.7B 4-bit1.6232card

Data mix overview

Training data included persona SFT, OpenAI-expanded Franklin dialogue, thinking/identity reinforcement, OOD corrections, natural dialogue repair, tool-call cleanup, English-lock cleanup, 7B ChatML answer-clean rows, and targeted coherence/factual repair rows.

DatasetRows
franklin_7b_coherence_repair_v2.jsonl287
franklin_7b_factual_coherence_repair_v3.jsonl308
franklin_identity_reinforcement.jsonl212
franklin_negative_identity_thinking.jsonl829
franklin_persona_openai_expanded.jsonl891
franklin_persona_sft.jsonl288
franklin_qwen3_4b_answer_only.jsonl3253
franklin_qwen3_4b_english_lock_cleanup.jsonl816
franklin_qwen3_4b_toolcall_cleanup.jsonl920
franklin_qwen3_8b_chatml_answer_clean.jsonl2400
franklin_thinking_sft.jsonl1259
franklin_thinking_strong_reinforcement.jsonl575
franklin_v4_general_balanced_thinking.jsonl825
franklin_v5_out_of_domain_correction.jsonl684
franklin_v6_1_targeted_ood_fix.jsonl870
franklin_v6_contrastive_thinking.jsonl599
franklin_v6_contrastive_thinking_final.jsonl2684
franklin_v6_contrastive_thinking_weighted.jsonl1584
franklin_v7_natural_dialogue_repair.jsonl1830
franklin_v8_minimal_thought_repair.jsonl1040
franklin_v9_factual_dialogue.jsonl3019

How these models might be useful

Browse models

qwen2.5-7b-ben-franklin-v1-lite-r4-qv

Family: Qwen2.5 7B Instruct 4-bit · Size: 0.06 GB · LoRA: r=4 alpha=8 · model card

Benchmark: 30 · Flags: {'base_identity_leak': 1, 'overdenial': 1}

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Benchmark score: 30 with flags {'base_identity_leak': 1, 'overdenial': 1}.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen2.5-7b-ben-franklin-v1-lite-r4-qv

qwen2.5-7b-ben-franklin-v2-coherence-r4-qv

Family: Qwen2.5 7B Instruct 4-bit · Size: 0.06 GB · LoRA: r=4 alpha=8 · model card

Benchmark: 33 · Flags: {'base_identity_leak': 1}

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Best modest improvement over 7B v1 for coherence and reduced over-denial in the broad benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_coherence_repair_v2.jsonl: 287

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen2.5-7b-ben-franklin-v2-coherence-r4-qv

qwen2.5-7b-ben-franklin-v3-factual-coherence-r4-qv

Family: Qwen2.5 7B Instruct 4-bit · Size: 0.06 GB · LoRA: r=4 alpha=8 · model card

Benchmark: 35 · Flags: {'base_identity_leak': 1}

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Best numeric coherence benchmark score among evaluated 7B adapters.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.
  • Despite the name, not a clean factual fix: Craven Street answer still hallucinated.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_coherence_repair_v2.jsonl: 287
franklin_7b_factual_coherence_repair_v3.jsonl: 308

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen2.5-7b-ben-franklin-v3-factual-coherence-r4-qv

qwen2.5-7b-ben-franklin-v3c-factual-r8-qv-from-base

Family: Qwen2.5 7B Instruct 4-bit · Size: 0.08 GB · LoRA: r=8 alpha=16 · model card

Benchmark: 28 · Flags: {'base_identity_leak': 1, 'overdenial': 1}

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Proves r=8 q/v LoRA from clean 7B base can train on this 8GB GPU.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.
  • Regressed versus v1/v2/v3 in the coherence benchmark.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_factual_coherence_repair_v3.jsonl: 308

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen2.5-7b-ben-franklin-v3c-factual-r8-qv-from-base

qwen3-4b-instruct-2507-ben-franklin-v1-lora

Family: Qwen3 4B Instruct 4-bit · Size: 1.34 GB · LoRA: r=16 alpha=32 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Middle-size family: more capable than 1.7B while still comfortable on 8GB VRAM.
  • Several variants target ChatML/completion formatting, tool-call cleanup, and English-lock behavior.

Weaknesses

  • Some later 4B adapters, especially v5, know targeted facts but emit visible tool_call tags offline.
  • Can leak base-model identity or policy/meta phrasing depending on prompt path.

Data mix:
franklin_qwen3_4b_answer_only.jsonl: 3253

Compute: Inference/training: comfortable on RTX 3070 8GB in 4-bit. Full-module LoRA at r=16-32 was used historically; expect several GB VRAM and slower but practical training.

./adapters/qwen3-4b-instruct-2507-ben-franklin-v1-lora

qwen3-4b-instruct-2507-ben-franklin-v2-chatml-lora

Family: Qwen3 4B Instruct 4-bit · Size: 2.19 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Middle-size family: more capable than 1.7B while still comfortable on 8GB VRAM.
  • Several variants target ChatML/completion formatting, tool-call cleanup, and English-lock behavior.

Weaknesses

  • Some later 4B adapters, especially v5, know targeted facts but emit visible tool_call tags offline.
  • Can leak base-model identity or policy/meta phrasing depending on prompt path.

Data mix:
franklin_qwen3_4b_answer_only.jsonl: 3253

Compute: Inference/training: comfortable on RTX 3070 8GB in 4-bit. Full-module LoRA at r=16-32 was used historically; expect several GB VRAM and slower but practical training.

./adapters/qwen3-4b-instruct-2507-ben-franklin-v2-chatml-lora

qwen3-4b-instruct-2507-ben-franklin-v3-chatml-completions-lora

Family: Qwen3 4B Instruct 4-bit · Size: 2.19 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Middle-size family: more capable than 1.7B while still comfortable on 8GB VRAM.
  • Several variants target ChatML/completion formatting, tool-call cleanup, and English-lock behavior.

Weaknesses

  • Some later 4B adapters, especially v5, know targeted facts but emit visible tool_call tags offline.
  • Can leak base-model identity or policy/meta phrasing depending on prompt path.

Data mix:
franklin_qwen3_4b_answer_only.jsonl: 3253

Compute: Inference/training: comfortable on RTX 3070 8GB in 4-bit. Full-module LoRA at r=16-32 was used historically; expect several GB VRAM and slower but practical training.

./adapters/qwen3-4b-instruct-2507-ben-franklin-v3-chatml-completions-lora

qwen3-4b-instruct-2507-ben-franklin-v4-toolcall-clean-lora

Family: Qwen3 4B Instruct 4-bit · Size: 1.81 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Middle-size family: more capable than 1.7B while still comfortable on 8GB VRAM.
  • Several variants target ChatML/completion formatting, tool-call cleanup, and English-lock behavior.
  • Targeted cleanup of visible tool_call artifacts.

Weaknesses

  • Some later 4B adapters, especially v5, know targeted facts but emit visible tool_call tags offline.
  • Can leak base-model identity or policy/meta phrasing depending on prompt path.

Data mix:
franklin_qwen3_4b_toolcall_cleanup.jsonl: 920

Compute: Inference/training: comfortable on RTX 3070 8GB in 4-bit. Full-module LoRA at r=16-32 was used historically; expect several GB VRAM and slower but practical training.

./adapters/qwen3-4b-instruct-2507-ben-franklin-v4-toolcall-clean-lora

qwen3-4b-instruct-2507-ben-franklin-v5-english-lock-lora

Family: Qwen3 4B Instruct 4-bit · Size: 1.81 GB · LoRA: r=32 alpha=64 · model card

Benchmark: -92 · Flags: {'tool_call': 15, 'continuity_miss': 1}

Strengths

  • Middle-size family: more capable than 1.7B while still comfortable on 8GB VRAM.
  • Several variants target ChatML/completion formatting, tool-call cleanup, and English-lock behavior.
  • Contains useful cleaned English/factual phrasing, including better Craven/Hewson material.
  • Benchmark score: -92 with flags {'tool_call': 15, 'continuity_miss': 1}.

Weaknesses

  • Some later 4B adapters, especially v5, know targeted facts but emit visible tool_call tags offline.
  • Can leak base-model identity or policy/meta phrasing depending on prompt path.
  • Offline benchmark showed severe visible tool_call tag regression.

Data mix:
franklin_qwen3_4b_english_lock_cleanup.jsonl: 816

Compute: Inference/training: comfortable on RTX 3070 8GB in 4-bit. Full-module LoRA at r=16-32 was used historically; expect several GB VRAM and slower but practical training.

./adapters/qwen3-4b-instruct-2507-ben-franklin-v5-english-lock-lora

qwen3-1.7b-ben-franklin-identity-reinforced-lora

Family: Qwen3 1.7B 4-bit · Size: 0.99 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-identity-reinforced-lora

qwen3-1.7b-ben-franklin-openai-expanded-lora

Family: Qwen3 1.7B 4-bit · Size: 1.2 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-openai-expanded-lora

qwen3-1.7b-ben-franklin-thinking-lora

Family: Qwen3 1.7B 4-bit · Size: 0.99 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-lora

qwen3-1.7b-ben-franklin-thinking-v2-lora

Family: Qwen3 1.7B 4-bit · Size: 0.78 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_coherence_repair_v2.jsonl: 287

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v2-lora

qwen3-1.7b-ben-franklin-thinking-v3-negative-identity-lora

Family: Qwen3 1.7B 4-bit · Size: 0.78 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_factual_coherence_repair_v3.jsonl: 308

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v3-negative-identity-lora

qwen3-1.7b-ben-franklin-thinking-v4-balanced-lora

Family: Qwen3 1.7B 4-bit · Size: 0.78 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v4-balanced-lora

qwen3-1.7b-ben-franklin-thinking-v5-ood-fixed-lora

Family: Qwen3 1.7B 4-bit · Size: 0.78 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v5-ood-fixed-lora

qwen3-1.7b-ben-franklin-thinking-v6-1-ood-fixed-lora

Family: Qwen3 1.7B 4-bit · Size: 0.99 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v6-1-ood-fixed-lora

qwen3-1.7b-ben-franklin-thinking-v6-contrastive-lora

Family: Qwen3 1.7B 4-bit · Size: 1.62 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v6-contrastive-lora

qwen3-1.7b-ben-franklin-thinking-v7-natural-dialogue-lora

Family: Qwen3 1.7B 4-bit · Size: 1.2 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Focused on more natural short conversational replies.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v7-natural-dialogue-lora

qwen3-1.7b-ben-franklin-thinking-v8-minimal-thought-lora

Family: Qwen3 1.7B 4-bit · Size: 0.99 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Focused on reducing visible thought/over-reasoning style.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v8-minimal-thought-lora

qwen3-1.7b-ben-franklin-thinking-v9-factual-dialogue-lora

Family: Qwen3 1.7B 4-bit · Size: 1.62 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Focused on factual dialogue and hard Franklin biography prompts.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_factual_coherence_repair_v3.jsonl: 308

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v9-factual-dialogue-lora

qwen3-1.7b-ben-franklin-thinking-v9-from-v2-factual-dialogue-lora

Family: Qwen3 1.7B 4-bit · Size: 1.62 GB · LoRA: r=32 alpha=64 · model card

Benchmark: · Flags: not benchmarked

Strengths

  • Largest Benjamin Franklin LoRA family proven trainable on this RTX 3070 8GB machine.
  • Best base reasoning/coherence among the local Franklin adapters.
  • Good short-turn continuity in the coherence benchmark.
  • Focused on factual dialogue and hard Franklin biography prompts.

Weaknesses

  • Qwen2.5 7B base is already highly steerable, so improvements over the prompted base are modest.
  • q/v-only LoRA is weak for implanting stubborn factual corrections.
  • Craven Street/Hewson factuality remains unreliable unless retrieval/prompt context is supplied.

Data mix:
franklin_qwen3_8b_chatml_answer_clean.jsonl: 2400
franklin_7b_coherence_repair_v2.jsonl: 287
franklin_7b_factual_coherence_repair_v3.jsonl: 308

Compute: Inference: RTX 3070 8GB works in 4-bit with the adapter; expect roughly 6-7GB VRAM. Training proven only with q_proj/v_proj, r=4 or r=8, max_seq_length=512, batch_size=1, gradient_accumulation=16; full-module LoRA is not recommended on 8GB.

./adapters/qwen3-1.7b-ben-franklin-thinking-v9-from-v2-factual-dialogue-lora