ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : support glm3 and glm4 (#8031)

Browse source 
* add chatglm3-6b model support huggingface model:
 https://hf-mirror.com/THUDM/chatglm3-6b

Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com>

* remove .rotary_pos_emb.inv_freq and unuse code for chatglm3 model

Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com>

* fix lint error

Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com>

* optimize convert-hf-to-gguf.py for chatglm model

Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com>

* support glm-4-9b-chat

Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com>

* fix eos tokens to glm4

* remove unused log

* add preprocess to chatglm3 and chatglm4

* add eos_id_list to llama.cpp

* fix code style

* fix code style

* fix conflicts

* fix conflicts

* Revert "add eos_id_list to llama.cpp"

This reverts commit 3a4d5790bfdc205c5b658204239f168fc21cc1a8.

* set <|endoftext|> as eos and <|user|> as eot

* fix chat template bug

* add comment to glm prefix and suffix

* fix conflicts and add rope_ratio & ChatGLMForConditionalGeneration

* fix chat template bug

* fix codestyle

* fix conflicts

* modified the general name of glm model

* fix conflicts

* remove prefix and suffix

* use normal glm4 chattempalte & use LLM_FFN_SWIGLU in phi3

* fix: resolve Flake8 errors in `convert-hf-to-gguf.py`

- Fix E302 by adding two blank lines before top-level function definitions
- Replace print statements to fix NP100
- Fix E303 by ensuring only one blank line between lines of code

* fix rope ratio to solve incorrect answers

* fix by comments

---------

Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com>
Co-authored-by: XingXing Qiao <qiaoxx@dingdao.com>
Co-authored-by: Umpire2018 <138990495+Umpire2018@users.noreply.github.com>
This commit is contained in:
toyer 2024-07-07 20:52:10 +08:00 • committed by GitHub
parent b5040086d4
commit 905942abdb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 455 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

14
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
"embedding.word_embeddings", # chatglm
"transformer.token_embeddings", # openelm
"shared", # t5
),
@ -55,6 +56,7 @@ class TensorNameMap:
"output", # llama-pth bloom internlm2
"word_embeddings_for_head", # persimmon
"lm_head.linear", # phi2
"output_layer", # chatglm
),
# Output norm
@ -71,12 +73,14 @@ class TensorNameMap:
"model.norm_f", # mamba-qbert
"backbone.norm_f", # mamba
"transformer.rms_norm", # Grok
"encoder.final_layernorm", # chatglm
"transformer.norm", # openelm
),
# Rope frequencies
MODEL_TENSOR.ROPE_FREQS: (
"rope.freqs", # llama-pth
"rotary_pos_emb.inv_freq", # chatglm
),
}
@ -101,6 +105,7 @@ class TensorNameMap:
"backbone.layers.{bid}.norm", # mamba
"transformer.decoder_layer.{bid}.rms_norm", # Grok
"transformer.blocks.{bid}.norm_attn_norm.norm_1", # dbrx
"encoder.layers.{bid}.input_layernorm", # chatglm
"transformer.layers.{bid}.attn_norm", # openelm
),
@ -124,6 +129,7 @@ class TensorNameMap:
"transformer.h.{bid}.mixer.Wqkv", # phi2
"encoder.layers.{bid}.attn.Wqkv", # nomic-bert
"model.layers.{bid}.self_attn.qkv_proj", # phi3
"encoder.layers.{bid}.self_attention.query_key_value", # chatglm
"transformer.layers.{bid}.attn.qkv_proj", # openelm
),
@ -135,7 +141,7 @@ class TensorNameMap:
"transformer.h.{bid}.attn.q_proj", # gpt-j
"model.layers.layers.{bid}.self_attn.q_proj", # plamo
"model.layers.{bid}.attention.wq", # internlm2
"transformer.decoder_layer.{bid}.multi_head_attention.query" # Grok
"transformer.decoder_layer.{bid}.multi_head_attention.query",# Grok
),
# Attention key
@ -147,7 +153,7 @@ class TensorNameMap:
"transformer.h.{bid}.attn.k", # refact
"model.layers.layers.{bid}.self_attn.k_proj", # plamo
"model.layers.{bid}.attention.wk", # internlm2
"transformer.decoder_layer.{bid}.multi_head_attention.key" # Grok
"transformer.decoder_layer.{bid}.multi_head_attention.key",# Grok
),
# Attention value
@ -182,6 +188,7 @@ 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
"encoder.layers.{bid}.self_attention.dense", # chatglm
"transformer.layers.{bid}.attn.out_proj", # openelm
),
@ -218,6 +225,7 @@ class TensorNameMap:
"h.{bid}.ln_2", # gpt2
"model.layers.{bid}.ffn_norm", # internlm2
"transformer.decoder_layer.{bid}.rms_norm_2", # Grok
"encoder.layers.{bid}.post_attention_layernorm", # chatglm
"transformer.layers.{bid}.ffn_norm", # openelm
),
@ -268,6 +276,7 @@ class TensorNameMap:
"model.layers.{bid}.mlp.c_fc", # starcoder2
"encoder.layer.{bid}.mlp.gated_layers_v", # jina-bert-v2
"model.layers.{bid}.residual_mlp.w3", # arctic
"encoder.layers.{bid}.mlp.dense_h_to_4h", # chatglm
),
MODEL_TENSOR.FFN_UP_EXP: (
@ -337,6 +346,7 @@ class TensorNameMap:
"transformer.layers.{bid}.ffn.proj_2", # openelm
"model.layers.{bid}.residual_mlp.w2", # arctic
"encoder.layer.{bid}.mlp.down_layer", # jina-bert-v2
"encoder.layers.{bid}.mlp.dense_4h_to_h", # chatglm
),
MODEL_TENSOR.FFN_DOWN_EXP: (