vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Initial OpenELM support (270M only so far)

Browse source
This commit is contained in:
Icecream95 2024-05-18 19:41:42 +12:00
parent c1b295eea5
commit 217d8d7b77
4 changed files with 322 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

17
gguf-py/gguf/tensor_mapping.py
View file

@ -24,6 +24,7 @@ class TensorNameMap:
"backbone.embedding", # mamba
"backbone.embeddings", # mamba-hf
"transformer.in_out_embed", # Grok
"transformer.token_embeddings", # openelm
),
# Token type embeddings
@ -36,6 +37,7 @@ class TensorNameMap:
"word_embeddings_layernorm", # bloom
"embeddings.LayerNorm", # bert
"emb_ln", # nomic-bert
"transformer.norm", # openelm
),
# Position embeddings
@ -68,6 +70,7 @@ class TensorNameMap:
"model.norm_f", # mamba-qbert
"backbone.norm_f", # mamba
"transformer.rms_norm", # Grok
"transformer.norm", # openelm
),
# Rope frequencies
@ -97,6 +100,7 @@ class TensorNameMap:
"backbone.layers.{bid}.norm", # mamba
"transformer.decoder_layer.{bid}.rms_norm", # Grok
"transformer.blocks.{bid}.norm_attn_norm.norm_1", # dbrx
"transformer.layers.{bid}.attn_norm", # openelm
),
# Attention norm 2
@ -117,7 +121,8 @@ class TensorNameMap:
"h.{bid}.attn.c_attn", # gpt2
"transformer.h.{bid}.mixer.Wqkv", # phi2
"encoder.layers.{bid}.attn.Wqkv", # nomic-bert
"model.layers.{bid}.self_attn.qkv_proj" # phi3
"model.layers.{bid}.self_attn.qkv_proj", # phi3
"transformer.layers.{bid}.attn.qkv_proj", # openelm
),
# Attention query
@ -175,6 +180,7 @@ class TensorNameMap:
"encoder.layers.{bid}.attn.out_proj", # nomic-bert
"transformer.decoder_layer.{bid}.multi_head_attention.linear", # Grok
"transformer.blocks.{bid}.norm_attn_norm.attn.out_proj", # dbrx
"transformer.layers.{bid}.attn.out_proj", # openelm
),
# Attention output norm
@ -206,6 +212,7 @@ class TensorNameMap:
"h.{bid}.ln_2", # gpt2
"model.layers.{bid}.ffn_norm", # internlm2
"transformer.decoder_layer.{bid}.rms_norm_2", # Grok
"transformer.layers.{bid}.ffn_norm", # openelm
),
MODEL_TENSOR.FFN_GATE_INP: (
@ -244,6 +251,7 @@ class TensorNameMap:
"encoder.layers.{bid}.mlp.fc11", # nomic-bert
"model.layers.{bid}.mlp.c_fc", # starcoder2
"encoder.layer.{bid}.mlp.gated_layers_v", # jina-bert-v2
"transformer.layers.{bid}.ffn.proj_1", # openelm
),
MODEL_TENSOR.FFN_UP_EXP: (
@ -306,6 +314,7 @@ class TensorNameMap:
"encoder.layers.{bid}.mlp.fc2", # nomic-bert
"model.layers.{bid}.mlp.c_proj", # starcoder2
"encoder.layer.{bid}.mlp.wo", # jina-bert-v2
"transformer.layers.{bid}.ffn.proj_2", # openelm
),
MODEL_TENSOR.FFN_DOWN_EXP: (
@ -324,7 +333,8 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.q_layernorm", # persimmon
"model.layers.{bid}.self_attn.q_norm", # cohere
"transformer.blocks.{bid}.attn.q_ln", # sea-lion
"encoder.layer.{bid}.attention.self.layer_norm_q" # jina-bert-v2
"encoder.layer.{bid}.attention.self.layer_norm_q", # jina-bert-v2
"transformer.layers.{bid}.attn.q_norm", # openelm
),
MODEL_TENSOR.ATTN_K_NORM: (
@ -332,7 +342,8 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.k_layernorm", # persimmon
"model.layers.{bid}.self_attn.k_norm", # cohere
"transformer.blocks.{bid}.attn.k_ln", # sea-lion
"encoder.layer.{bid}.attention.self.layer_norm_k" # jina-bert-v2
"encoder.layer.{bid}.attention.self.layer_norm_k", # jina-bert-v2
"transformer.layers.{bid}.attn.k_norm", # openelm
),
MODEL_TENSOR.ROPE_FREQS: (