Skip to content

Jais tests #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Jais tests #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions convert-hf-to-gguf-update.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,7 @@ class TOKENIZER_TYPE(IntEnum):
{"name": "jina-v2-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
{"name": "smaug-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct", },
{"name": "jina-v2-code", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-code", },
{"name": "jais", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/core42/jais-13b", },
]


Expand Down
85 changes: 76 additions & 9 deletions convert-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -421,9 +421,6 @@ def get_vocab_base_pre(self, tokenizer) -> str:
# NOTE: if you get an error here, you need to update the convert-hf-to-gguf-update.py script
# or pull the latest version of the model from Huggingface
# don't edit the hashes manually!
if chkhsh == "0ef9807a4087ebef797fc749390439009c3b9eda9ad1a097abbe738f486c01e5":
# ref: https://huggingface.co/meta-llama/Meta-Llama-3-8B
res = "llama-bpe"
if chkhsh == "049ecf7629871e3041641907f3de7c733e4dbfdc736f57d882ba0b0845599754":
# ref: https://huggingface.co/deepseek-ai/deepseek-llm-7b-base
res = "deepseek-llm"
Expand Down Expand Up @@ -451,18 +448,12 @@ def get_vocab_base_pre(self, tokenizer) -> str:
if chkhsh == "6221ad2852e85ce96f791f476e0b390cf9b474c9e3d1362f53a24a06dc8220ff":
# ref: https://huggingface.co/smallcloudai/Refact-1_6-base
res = "refact"
if chkhsh == "9c2227e4dd922002fb81bde4fc02b0483ca4f12911410dee2255e4987644e3f8":
# ref: https://huggingface.co/CohereForAI/c4ai-command-r-v01
res = "command-r"
if chkhsh == "e636dc30a262dcc0d8c323492e32ae2b70728f4df7dfe9737d9f920a282b8aea":
# ref: https://huggingface.co/Qwen/Qwen1.5-7B
res = "qwen2"
if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
# ref: https://huggingface.co/allenai/OLMo-1.7-7B-hf
res = "olmo"
if chkhsh == "a8594e3edff7c29c003940395316294b2c623e09894deebbc65f33f1515df79e":
# ref: https://huggingface.co/databricks/dbrx-base
res = "dbrx"
if chkhsh == "0876d13b50744004aa9aeae05e7b0647eac9d801b5ba4668afc01e709c15e19f":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-en
res = "jina-v2-en"
Expand All @@ -478,6 +469,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
if chkhsh == "7967bfa498ade6b757b064f31e964dddbb80f8f9a4d68d4ba7998fcf281c531a":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-code
res = "jina-v2-code"
if chkhsh == "b53802fb28e26d645c3a310b34bfe07da813026ec7c7716883404d5e0f8b1901":
# ref: https://huggingface.co/core42/jais-13b
res = "jais"

if res is None:
logger.warning("\n")
Expand Down Expand Up @@ -2713,6 +2707,79 @@ def write_tensors(self):
if len(experts) > 0:
raise ValueError(f"Unprocessed experts: {experts}")

@Model.register("JAISLMHeadModel")
class JaisModel(Model):
model_arch = gguf.MODEL_ARCH.JAIS

def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)

# SwigLU activation
assert self.hparams["activation_function"] == "swiglu"
# ALiBi position embedding
assert self.hparams["position_embedding_type"] == "alibi"

# Embeddings scale
self.embeddings_scale = 1.0
# note: For some JAIS flavors, output is tied to (same as) wte in original model
self.output_is_wte = False
if 'mup_embeddings_scale' in self.hparams:
self.output_is_wte = True # Hack (?)
self.embeddings_scale = self.hparams['mup_embeddings_scale']
elif 'embeddings_scale' in self.hparams:
self.embeddings_scale = self.hparams['embeddings_scale']
else:
assert False

self.width_scale = 1.0
if 'mup_output_alpha' in self.hparams:
assert 'mup_width_scale' in self.hparams
self.width_scale = self.hparams['mup_output_alpha'] * self.hparams['mup_width_scale']
elif 'width_scale' in self.hparams:
self.width_scale = self.hparams['width_scale']
else:
assert False

def set_vocab(self):
self._set_vocab_gpt2()

def set_gguf_parameters(self):
self.gguf_writer.add_name(self.dir_model.name)
self.gguf_writer.add_block_count(self.hparams["n_layer"])
self.gguf_writer.add_context_length(self.hparams["n_positions"])
self.gguf_writer.add_embedding_length(self.hparams["n_embd"])
self.gguf_writer.add_feed_forward_length(self.hparams["n_inner"])
self.gguf_writer.add_head_count(self.hparams["n_head"])
self.gguf_writer.add_layer_norm_eps(self.hparams["layer_norm_epsilon"])
self.gguf_writer.add_file_type(self.ftype)

def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
del bid # unused

tensors: list[tuple[str, Tensor]] = []

# we don't need these
if name.endswith((".attn.bias", "relative_pe.slopes")):
return tensors

if name.endswith((".c_attn.weight", ".c_proj.weight", ".c_fc.weight", ".c_fc2.weight")):
data_torch = data_torch.transpose(1, 0)

new_name = self.map_tensor_name(name)

if new_name == self.format_tensor_name(gguf.MODEL_TENSOR.TOKEN_EMBD):
tensors.append((new_name, data_torch * self.embeddings_scale))
if self.output_is_wte:
tensors.append((self.format_tensor_name(gguf.MODEL_TENSOR.OUTPUT), data_torch * self.width_scale))
elif new_name == self.format_tensor_name(gguf.MODEL_TENSOR.OUTPUT):
assert not self.output_is_wte
tensors.append((new_name, data_torch * self.width_scale))
else:
tensors.append((new_name, data_torch))

return tensors



###### CONVERSION LOGIC ######

Expand Down
1 change: 0 additions & 1 deletion examples/main/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -716,7 +716,6 @@ int main(int argc, char ** argv) {

// Console/Stream Output
fprintf(stdout, "%s", token_str.c_str());

// Record Displayed Tokens To Log
// Note: Generated tokens are created one by one hence this check
if (embd.size() > 1) {
Expand Down
2 changes: 1 addition & 1 deletion ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13954,13 +13954,13 @@ static void ggml_compute_forward_soft_max_f32(
} else {
for (int i = 0; i < nc; ++i) {
wp[i] += slope*mp_f32[i];

}
}
}

#ifndef NDEBUG
for (int i = 0; i < nc; ++i) {
//printf("p[%d] = %f\n", i, p[i]);
assert(!isnan(wp[i]));
}
#endif
Expand Down
14 changes: 14 additions & 0 deletions gguf-py/gguf/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,7 @@ class MODEL_ARCH(IntEnum):
OLMO = auto()
ARCTIC = auto()
DEEPSEEK2 = auto()
JAIS = auto()


class MODEL_TENSOR(IntEnum):
Expand Down Expand Up @@ -236,6 +237,7 @@ class MODEL_TENSOR(IntEnum):
MODEL_ARCH.OLMO: "olmo",
MODEL_ARCH.ARCTIC: "arctic",
MODEL_ARCH.DEEPSEEK2: "deepseek2",
MODEL_ARCH.JAIS: "jais",
}

TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
Expand Down Expand Up @@ -807,6 +809,18 @@ class MODEL_TENSOR(IntEnum):
MODEL_TENSOR.FFN_DOWN_SHEXP,
MODEL_TENSOR.FFN_UP_SHEXP,
],
MODEL_ARCH.JAIS: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_UP,
],
# TODO
}

Expand Down
19 changes: 10 additions & 9 deletions gguf-py/gguf/tensor_mapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ class TensorNameMap:
# Token embeddings
MODEL_TENSOR.TOKEN_EMBD: (
"gpt_neox.embed_in", # gptneox
"transformer.wte", # gpt2 gpt-j mpt refact qwen dbrx
"transformer.wte", # gpt2 gpt-j mpt refact qwen dbrx jais
"transformer.word_embeddings", # falcon
"word_embeddings", # bloom
"model.embed_tokens", # llama-hf
Expand Down Expand Up @@ -48,7 +48,7 @@ class TensorNameMap:
# Output
MODEL_TENSOR.OUTPUT: (
"embed_out", # gptneox
"lm_head", # gpt2 mpt falcon llama-hf baichuan qwen mamba dbrx
"lm_head", # gpt2 mpt falcon llama-hf baichuan qwen mamba dbrx jais
"output", # llama-pth bloom internlm2
"word_embeddings_for_head", # persimmon
"lm_head.linear", # phi2
Expand All @@ -57,7 +57,7 @@ class TensorNameMap:
# Output norm
MODEL_TENSOR.OUTPUT_NORM: (
"gpt_neox.final_layer_norm", # gptneox
"transformer.ln_f", # gpt2 gpt-j falcon
"transformer.ln_f", # gpt2 gpt-j falcon jais
"model.norm", # llama-hf baichuan internlm2
"norm", # llama-pth
"transformer.norm_f", # mpt dbrx
Expand All @@ -80,7 +80,7 @@ class TensorNameMap:
# Attention norm
MODEL_TENSOR.ATTN_NORM: (
"gpt_neox.layers.{bid}.input_layernorm", # gptneox
"transformer.h.{bid}.ln_1", # gpt2 gpt-j refact qwen
"transformer.h.{bid}.ln_1", # gpt2 gpt-j refact qwen jais
"transformer.blocks.{bid}.norm_1", # mpt
"transformer.h.{bid}.input_layernorm", # falcon7b
"h.{bid}.input_layernorm", # bloom
Expand Down Expand Up @@ -108,7 +108,7 @@ class TensorNameMap:
# Attention query-key-value
MODEL_TENSOR.ATTN_QKV: (
"gpt_neox.layers.{bid}.attention.query_key_value", # gptneox
"transformer.h.{bid}.attn.c_attn", # gpt2 qwen
"transformer.h.{bid}.attn.c_attn", # gpt2 qwen jais
"transformer.blocks.{bid}.attn.Wqkv", # mpt
"transformer.blocks.{bid}.norm_attn_norm.attn.Wqkv", # dbrx
"transformer.h.{bid}.self_attention.query_key_value", # falcon
Expand Down Expand Up @@ -159,7 +159,7 @@ class TensorNameMap:
# Attention output
MODEL_TENSOR.ATTN_OUT: (
"gpt_neox.layers.{bid}.attention.dense", # gptneox
"transformer.h.{bid}.attn.c_proj", # gpt2 refact qwen
"transformer.h.{bid}.attn.c_proj", # gpt2 refact qwen jais
"transformer.blocks.{bid}.attn.out_proj", # mpt
"transformer.h.{bid}.self_attention.dense", # falcon
"h.{bid}.self_attention.dense", # bloom
Expand Down Expand Up @@ -197,7 +197,7 @@ class TensorNameMap:
# Feed-forward norm
MODEL_TENSOR.FFN_NORM: (
"gpt_neox.layers.{bid}.post_attention_layernorm", # gptneox
"transformer.h.{bid}.ln_2", # gpt2 refact qwen
"transformer.h.{bid}.ln_2", # gpt2 refact qwen jais
"h.{bid}.post_attention_layernorm", # bloom
"transformer.blocks.{bid}.norm_2", # mpt
"model.layers.{bid}.post_attention_layernorm", # llama-hf
Expand All @@ -224,7 +224,7 @@ class TensorNameMap:
# Feed-forward up
MODEL_TENSOR.FFN_UP: (
"gpt_neox.layers.{bid}.mlp.dense_h_to_4h", # gptneox
"transformer.h.{bid}.mlp.c_fc", # gpt2
"transformer.h.{bid}.mlp.c_fc", # gpt2 jais
"transformer.blocks.{bid}.ffn.up_proj", # mpt
"transformer.h.{bid}.mlp.dense_h_to_4h", # falcon
"h.{bid}.mlp.dense_h_to_4h", # bloom
Expand Down Expand Up @@ -270,6 +270,7 @@ class TensorNameMap:
"model.layers.{bid}.mlp.gate_proj", # llama-hf refact
"layers.{bid}.feed_forward.w1", # llama-pth
"transformer.h.{bid}.mlp.w2", # qwen
"transformer.h.{bid}.mlp.c_fc2", # jais
"model.layers.layers.{bid}.mlp.gate_proj", # plamo
"model.layers.{bid}.feed_forward.w1", # internlm2
"encoder.layers.{bid}.mlp.fc12", # nomic-bert
Expand All @@ -293,7 +294,7 @@ class TensorNameMap:
# Feed-forward down
MODEL_TENSOR.FFN_DOWN: (
"gpt_neox.layers.{bid}.mlp.dense_4h_to_h", # gptneox
"transformer.h.{bid}.mlp.c_proj", # gpt2 refact qwen
"transformer.h.{bid}.mlp.c_proj", # gpt2 refact qwen jais
"transformer.blocks.{bid}.ffn.down_proj", # mpt
"transformer.h.{bid}.mlp.dense_4h_to_h", # falcon
"h.{bid}.mlp.dense_4h_to_h", # bloom
Expand Down
Loading