Gemma 4 E4B Sol Traces v4
Targeted routing-repair continuation from v3. Continuation-trained on 125 mined trajectories (SWE-bench, synthetic, bash history, GitHub commits) to fix runcommand, searchcode, and applypatch tool selection.
Source du modèle
- Type
- LoRA
- Taille du fichier
- 41,6 MB
- Modèle de base
- unsloth/gemma-4-E4B-it
- Version
- vadapter_model
- Mis à jour
- 14 oct. 2026
- Téléchargements
- 24
- Source
- Hugging Face
Description de la source
Gemma-4-E4B-Sol-Traces-v4
Targeted routing-repair continuation from v3. Continuation-trained on 125 mined trajectories (SWE-bench, synthetic, bash history, GitHub commits) to fix run_command, search_code, and apply_patch tool selection.
Training
| Parameter | Value |
|---|---|
| Base model | unsloth/gemma-4-E4B-it |
| Adapter start | v3 from-scratch (336 LoRA keys) |
| Training type | Continuation (100 steps) |
| Dataset | 125 train / 15 val / 17 test |
| Sources | SWE-bench (50), synthetic (50), bash history (55), GitHub (2) |
| Tool schema | 6 tools (search_code, run_command, apply_patch, read_file, list_files, write_file) |
| Learning rate | 3e-5, cosine, 3% warmup |
| Batch | 1 × 8 grad accum |
| Runtime | 12 min on H100 |
| Training loss | 0.093 |
| Eval loss | 0.671 |
| Cost | ~$0.80 |
Routing Improvement
| Tool | v1 | v2 | v3 | v4 |
|---|---|---|---|---|
| run_command | 2/5 | 0/5 | 0/5 | 5/5 ✅ |
| search_code | 0/5 | 0/5 | 0/5 | 1/5 |
| apply_patch | 1/5 | 0/5 | 0/5 | 0/5 |
| list_files | 5/5 | 5/5 | 5/5 | 4/5 |
| read_file | 4/5 | 5/5 | 5/5 | 5/5 |
| no-tool | 4/5 | 5/5 | 5/5 | 3/5 |
| Overall | 53% | 50% | 50% | 60% |
Files
| File | Size |
|---|---|
gemma-4-e4b-sol-traces-v4-Q4_K_M.gguf | 4.97 GiB |
gemma-4-e4b-sol-traces-v4-f16.gguf | 14.02 GiB |
adapter/adapter_model.safetensors | 35 MiB |
training_stats.json | — |
Usage
llama-cli -m gemma-4-e4b-sol-traces-v4-Q4_K_M.gguf -ngl 99
Sources
1 source
Sources
1 sourceVérifié 23 août
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactadapter/adapter_model.safetensors
safetensors · 41,6 MB · SHA-256 fd6151eefe02…590a · Hugging Face
Download fileExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: gemma language: - en tags: - agentic - tool-calling - function-calling - code-agent - gemma-4 - e4b - lora - unsloth - sol-traces - hermes-agent base_model: unsloth/gemma-4-E4B-it library_name: gguf inference: false --- # Gemma-4-E4B-Sol-Traces-v4 **Targeted routing-repair continuation** from v3. Continuation-trained on 125 mined trajectories (SWE-bench, synthetic, bash history, GitHub commits) to fix `run_command`, `search_code`, and `apply_patch` tool selection. ## Training | Parameter | Value | |---|---| | Base model | `unsloth/gemma-4-E4B-it` | | Adapter start | v3 from-scratch (336 LoRA keys) | | Training type | Continuation (100 steps) | | Dataset | 125 train / 15 val / 17 test | | Sources | SWE-bench (50), synthetic (50), bash history (55), GitHub (2) | | Tool schema | 6 tools (search_code, run_command, apply_patch, read_file, list_files, write_file) | | Learning rate | 3e-5, cosine, 3% warmup | | Batch | 1 × 8 grad accum | | Runtime | 12 min on H100 | | Training loss | 0.093 | | Eval loss | 0.671 | | Cost | ~$0.80 | ## Routing Improvement | Tool | v1 | v2 | v3 | **v4** | |---|---|---|---|---| | run_command | 2/5 | 0/5 | 0/5 | **5/5** ✅ | | search_code | 0/5 | 0/5 | 0/5 | **1/5** | | apply_patch | 1/5 | 0/5 | 0/5 | 0/5 | | list_files | 5/5 | 5/5 | 5/5 | 4/5 | | read_file | 4/5 | 5/5 | 5/5 | 5/5 | | no-tool | 4/5 | 5/5 | 5/5 | 3/5 | | **Overall** | 53% | 50% | 50% | **60%** | ## Files | File | Size | |---|---| | `gemma-4-e4b-sol-traces-v4-Q4_K_M.gguf` | 4.97 GiB | | `gemma-4-e4b-sol-traces-v4-f16.gguf` | 14.02 GiB | | `adapter/adapter_model.safetensors` | 35 MiB | | `training_stats.json` | — | ## Usage ```bash llama-cli -m gemma-4-e4b-sol-traces-v4-Q4_K_M.gguf -ngl 99 ```
Source context: 24 downloads · 0 likes · Library gguf · Repo RedTeamLab/Gemma-4-E4B-Sol-Traces-v4
