chatlearn/utils/vllm_utils.py [873:892]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        hf_config.vocab_size = word_embeddings.shape[0]

    # Transformer Layers
    print("Converting transformer layers")
    if CURRENT_VLLM_VERSION in [VLLMVersion.v_0_6_3, VLLMVersion.v_0_6_6]:
        start_layer_idx, _ = get_pp_indices(
            hf_config.num_hidden_layers,
            pp_rank,
            pp_size
        )
        layer_offset = start_layer_idx
    else:
        assert pp_size == 1, f"expect pipeline parallel size eq 1 for vllm {CURRENT_VLLM_VERSION}"
        layer_offset = hf_config.num_hidden_layers // pp_size * pp_rank
    # The transformer.
    path = (
        "model.language_model.transformer"
        if "transformer" in get_element_from_dict_by_path(tp_state_dicts[0], "model.language_model").keys()
        else "model.language_model.encoder"
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



chatlearn/utils/vllm_utils.py [1238:1258]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            hf_config.vocab_size = word_embeddings.shape[0]

    # Transformer Layers
    print("Converting transformer layers")
    if CURRENT_VLLM_VERSION in [VLLMVersion.v_0_6_3, VLLMVersion.v_0_6_6]:
        start_layer_idx, _ = get_pp_indices(
            hf_config.num_hidden_layers,
            pp_rank,
            pp_size
        )
        layer_offset = start_layer_idx
    else:
        assert pp_size == 1, f"expect pipeline parallel size eq 1 for vllm {CURRENT_VLLM_VERSION}"
        layer_offset = hf_config.num_hidden_layers // pp_size * pp_rank

    # The transformer.
    path = (
        "model.language_model.transformer"
        if "transformer" in get_element_from_dict_by_path(tp_state_dicts[0], "model.language_model").keys()
        else "model.language_model.encoder"
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -