Skip to content
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

Updated real_models list #1459

Merged
merged 1 commit into from
Jan 1, 2025
Merged

Updated real_models list #1459

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
27 changes: 18 additions & 9 deletions tests/python_tests/models/real_models
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ EleutherAI/gpt-neo-2.7B
EleutherAI/gpt-neox-20b
EleutherAI/pythia-160m
GAIR/Abel-7B-002
# OrionStarAI/Orion-14B-Base: pip install flash_attn (https://github.com/huggingface/transformers/pull/30954)
OrionStarAI/Orion-14B-Base
PygmalionAI/pygmalion-6b
Qwen/Qwen-7B
Qwen/Qwen-7B-Chat
Expand All @@ -21,6 +21,8 @@ Qwen/Qwen1.5-7B
Qwen/Qwen1.5-7B-Chat
Qwen/Qwen1.5-MoE-A2.7B
Qwen/Qwen1.5-MoE-A2.7B-Chat
Qwen/Qwen2-7B
Qwen/Qwen2-7B-Instruct
Salesforce/codegen-350M-multi
Salesforce/codegen-350M-nl
Salesforce/codegen2-1b
Expand Down Expand Up @@ -48,15 +50,16 @@ bigscience/bloomz-1b7
bigscience/bloomz-560m
bigscience/bloomz-7b1
cerebras/Cerebras-GPT-13B
# core42/jais-13b: wrong output with PA
# core42/jais-13b-chat: wrong output with PA
core42/jais-13b
core42/jais-13b-chat
databricks/dolly-v1-6b
databricks/dolly-v2-3b
# deepseek-ai/deepseek-coder-33b-instruct: OpenVINO tokenizers - Cannot convert tokenizer of this type without `.model` file
# deepseek-ai/deepseek-coder-6.7b-instruct: OpenVINO tokenizers - Cannot convert tokenizer of this type without `.model` file
# deepseek-ai/deepseek-moe-16b-base: optimum - Trying to export a deepseek model, that is a custom or unsupported architecture
# facebook/blenderbot-3B: optimum - IndexError: tuple index out of range
# facebook/incoder-1B: CB - Failed to detect "eos_token_id" in openvino_tokenizer.xml runtime information
deepseek-ai/deepseek-moe-16b-base
deepseek-ai/DeepSeek-V3-Base
facebook/blenderbot-3B
facebook/incoder-1B
facebook/opt-1.3b
facebook/opt-125m
facebook/opt-2.7b
Expand All @@ -66,6 +69,7 @@ google/gemma-1.1-7b-it
google/gemma-2b
google/gemma-2b-it
google/gemma-7b
google/gemma-2-9b
google/pegasus-big_patent
google/pegasus-large
gpt2
Expand All @@ -86,6 +90,10 @@ microsoft/DialoGPT-medium
microsoft/Orca-2-7b
microsoft/Phi-3-mini-128k-instruct
microsoft/Phi-3-mini-4k-instruct
microsoft/Phi-3-medium-128k-instruct
microsoft/Phi-3-small-8k-instruct
microsoft/Phi-3-small-128k-instruct
microsoft/Phi-3.5-MoE-instruct
# microsoft/biogpt: OpenVINO Tokenizers - openvino.runtime.exceptions.OVTypeError: Tokenizer type is not supported: <class 'transformers.models.biogpt.tokenization_biogpt.BioGptTokenizer'>
microsoft/phi-1_5
microsoft/phi-2
Expand All @@ -106,10 +114,10 @@ openbmb/MiniCPM-2B-dpo-bf16
openbmb/MiniCPM-2B-sft-bf16
openchat/openchat_3.5
openlm-research/open_llama_13b
# openlm-research/open_llama_3b: CPU - head size must be multiple of 16, current: 100
# openlm-research/open_llama_3b_v2: CPU - head size must be multiple of 16, current: 100
openlm-research/open_llama_3b
openlm-research/open_llama_3b_v2
# replit/replit-code-v1-3b: OpenVINO Tokenizers - AttributeError: 'ReplitLMTokenizer' object has no attribute 'sp_model'
# rinna/bilingual-gpt-neox-4b: OpenVINO Tokenizers - trash output (https://jira.devtools.intel.com/browse/CVS-142063)
rinna/bilingual-gpt-neox-4b
rinna/youri-7b-chat
stabilityai/stable-code-3b
stabilityai/stable-zephyr-3b
Expand All @@ -120,3 +128,4 @@ tiiuae/falcon-rw-7b
togethercomputer/RedPajama-INCITE-Chat-3B-v1
# xverse/XVERSE-7B-Chat: Transformers - Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 78 column 3
# xverse/XVERSE-MoE-A4.2B: Transformers - Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 78 column 3
Deci/DeciLM-7B
Loading