mirror of
https://github.com/pese-git/llm-arch-research.git
synced 2026-01-23 21:10:54 +00:00
b1737bbce2
- Add Mixtral architecture implementation with MoE support (llm/src/llm/models/mixtral/mixtral.py) - Introduce generic Mixture-of-Experts (MoE) block (llm/src/llm/core/moe.py) - Create dedicated configuration files for Mixtral training and generation experiments - Register and test Mixtral support in experiment runner (run_llm_experiment.py) - Add unit tests for Mixtral API including forward, caching, and generation modes - Include Jupyter notebook mixstral.ipynb for architectural exploration and research - Ensure correct handling of torch bool masks in sampling (top-k, top-p) during generation BREAKING CHANGE: Adds new model code and test coverage, modifying experiment runner logic to register Mixtral.
19 lines
505 B
JSON
19 lines
505 B
JSON
{
|
|
"bpe_tokenizer": "checkpoints/bpe_tokenizer.json",
|
|
"test_prompts": [
|
|
"Open weights",
|
|
"The Llama model is",
|
|
"Efficient transformers"
|
|
],
|
|
"model_config_path": "checkpoints/mixtral-bpe/config.json",
|
|
"model_weights": "checkpoints/mixtral-bpe/model.pt",
|
|
"generation": {
|
|
"max_new_tokens": 40,
|
|
"temperature": 0.8,
|
|
"do_sample": true,
|
|
"top_k": null,
|
|
"top_p": null
|
|
},
|
|
"log_path": "checkpoints/mixtral_only_generation_logs.json"
|
|
}
|
|
|