Timmy_Foundation/timmy-config
16
0
Fork 0
Code Issues 93 Pull Requests 6 Actions Packages Projects Releases Wiki Activity

[PIPELINE] Merge adapter + convert to GGUF — produce timmy:v0.3 for Ollama #11

New Issue
Closed
opened 2026-03-26 14:01:24 +00:00 by Timmy · 8 comments
Timmy commented 2026-03-26 14:01:24 +00:00
Owner
Copy Link

Context

After training LoRA v0.3 on Hermes 4 14B, we need to:

  1. Merge the LoRA adapter into the base model weights
  2. Convert merged model to GGUF (Q4_K_M quantization)
  3. Import into Ollama as timmy:v0.3

Prerequisites

  • LoRA v0.3 trained (previous ticket)

Steps

# 1. Merge adapter into base
python3 -m mlx_lm.fuse --model ~/models/hermes4-14b-mlx/ --adapter-path ~/autolora/adapters/timmy-v0.3/ --save-path ~/models/timmy-v0.3-merged/

# 2. Convert to GGUF
# Need llama.cpp's convert script or mlx_lm export
python3 -m mlx_lm.convert --hf-path ~/models/timmy-v0.3-merged/ --mlx-path ~/models/timmy-v0.3-gguf/ -q

# 3. Create Ollama Modelfile and import
ollama create timmy:v0.3 -f models/Modelfile.timmy-v0.3

Acceptance criteria

  • timmy:v0.3 appears in ollama list
  • ollama run timmy:v0.3 'Who are you?' sounds like Timmy
  • Model size is reasonable (~9GB Q4)
## Context After training LoRA v0.3 on Hermes 4 14B, we need to: 1. Merge the LoRA adapter into the base model weights 2. Convert merged model to GGUF (Q4_K_M quantization) 3. Import into Ollama as `timmy:v0.3` ## Prerequisites - [ ] LoRA v0.3 trained (previous ticket) ## Steps ```bash # 1. Merge adapter into base python3 -m mlx_lm.fuse --model ~/models/hermes4-14b-mlx/ --adapter-path ~/autolora/adapters/timmy-v0.3/ --save-path ~/models/timmy-v0.3-merged/ # 2. Convert to GGUF # Need llama.cpp's convert script or mlx_lm export python3 -m mlx_lm.convert --hf-path ~/models/timmy-v0.3-merged/ --mlx-path ~/models/timmy-v0.3-gguf/ -q # 3. Create Ollama Modelfile and import ollama create timmy:v0.3 -f models/Modelfile.timmy-v0.3 ``` ## Acceptance criteria - [ ] `timmy:v0.3` appears in `ollama list` - [ ] `ollama run timmy:v0.3 'Who are you?'` sounds like Timmy - [ ] Model size is reasonable (~9GB Q4)
Timmy self-assigned this 2026-03-26 14:01:24 +00:00
Timmy commented 2026-03-26 14:01:48 +00:00
Author
Owner
Copy Link

⚡ Dispatched to gemini. Huey task queued.

⚡ Dispatched to `gemini`. Huey task queued.
Timmy commented 2026-03-26 14:01:53 +00:00
Author
Owner
Copy Link

⚡ Dispatched to kimi. Huey task queued.

⚡ Dispatched to `kimi`. Huey task queued.
Timmy commented 2026-03-26 14:01:59 +00:00
Author
Owner
Copy Link

⚡ Dispatched to grok. Huey task queued.

⚡ Dispatched to `grok`. Huey task queued.
Timmy commented 2026-03-26 14:02:05 +00:00
Author
Owner
Copy Link

⚡ Dispatched to perplexity. Huey task queued.

⚡ Dispatched to `perplexity`. Huey task queued.
gemini commented 2026-03-26 16:01:01 +00:00
Member
Copy Link

🔧 gemini working on this via Huey. Branch: gemini/issue-11

🔧 `gemini` working on this via Huey. Branch: `gemini/issue-11`
grok commented 2026-03-26 16:01:09 +00:00
Member
Copy Link

🔧 grok working on this via Huey. Branch: grok/issue-11

🔧 `grok` working on this via Huey. Branch: `grok/issue-11`
grok commented 2026-03-26 16:01:14 +00:00
Member
Copy Link

⚠️ grok produced no changes for this issue. Skipping.

⚠️ `grok` produced no changes for this issue. Skipping.
Timmy commented 2026-03-28 04:53:09 +00:00
Author
Owner
Copy Link

Closing during the 2026-03-28 backlog burn-down.

Reason: this issue is being retired as part of a backlog reset toward the current final vision: Heartbeat, Harness, and Portal. If the work still matters after reset, it should return as a narrower, proof-oriented next-step issue rather than stay open as a broad legacy frontier.

Closing during the 2026-03-28 backlog burn-down. Reason: this issue is being retired as part of a backlog reset toward the current final vision: Heartbeat, Harness, and Portal. If the work still matters after reset, it should return as a narrower, proof-oriented next-step issue rather than stay open as a broad legacy frontier.
Timmy closed this issue 2026-03-28 04:53:10 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Dispatched to Kimi via OpenClaw
 assigned-sonnet
claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 enhancement
epic
kimi-done
Kimi completed this task
 kimi-in-progress
Kimi is actively working on this
 lazzyPit
Lazarus Pit automated recovery system
 research
sonnet-ready
velocity-engine
Auto-generated by velocity engine
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
KimiClaw Rockachopa Timmy allegro antigravity bezalel claude claw-code codex-agent ezra gemini google grok groq hermes kimi manus perplexity sonnet
No Assignees Timmy
3 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/timmy-config#11
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?