Upload folder using huggingface_hub (#1)

- bd00723e9089bd5ed1ceefbafa95216c26cf963ba7fd75ad445f62d1c439407d (1c7415cf6fcc16325969b600d68152b90c2387a5)
- a18289fa20d2f3d37198225c673d7541f3bb26afc9f5ac2578fe552a54290f66 (d55aca5b33ea7445dcd7b4cd2288b2ea65cbd216)

README.md

@@ -0,0 +1,85 @@
+---
+thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
+base_model: huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated
+metrics:
+- memory_disk
+- memory_inference
+- inference_latency
+- inference_throughput
+- inference_CO2_emissions
+- inference_energy_consumption
+tags:
+- pruna-ai
+---
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+    <a href="https://docs.pruna.ai/en/latest/setup/pip.html" target="_blank" rel="noopener noreferrer">
+        <img src="https://imgur.com/rVAgqMY.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+    </a>
+</div>
+<!-- header end -->
+
+[![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI)
+[![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI)
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/rskEr4BZJx)
+
+# Simply make AI models cheaper, smaller, faster, and greener!
+
+- Give a thumbs up if you like this model!
+- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
+- Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
+- Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
+- Join Pruna AI community on Discord [here](https://discord.gg/CP4VSgck) to share feedback/suggestions or get help.
+
+## Results
+
+![image info](./plots.png)
+
+**Frequently Asked Questions**
+- ***How does the compression work?*** The model is compressed with llm-int8.
+- ***How does the model quality change?*** The quality of the model output might vary compared to the base model.
+- ***How is the model efficiency evaluated?*** These results were obtained with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.
+- ***What is the model format?*** We use safetensors.
+- ***What calibration data has been used?*** If needed by the compression method, we used WikiText as the calibration data.
+- ***What is the naming convention for Pruna Huggingface models?*** We take the original model name and append "turbo", "tiny", or "green" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.
+- ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
+- ***What are "first" metrics?*** Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.
+- ***What are "Sync" and "Async" metrics?*** "Sync" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. "Async" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.
+
+## Setup
+
+You can run the smashed model with these steps:
+
+0. Check requirements from the original repo huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated installed. In particular, check python, cuda, and transformers versions.
+1. Make sure that you have installed quantization related packages.
+    ```bash
+    pip install transformers accelerate bitsandbytes>0.37.0
+    ```
+2. Load & run the model.
+    ```python 
+   from transformers import AutoModelForCausalLM, AutoTokenizer
+   
+
+   model = AutoModelForCausalLM.from_pretrained("PrunaAI/huihui-ai-EXAONE-3.5-2.4B-Instruct-abliterated-bnb-8bit-smashed", trust_remote_code=True, device_map='auto')
+   tokenizer = AutoTokenizer.from_pretrained("huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated")
+    
+   input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
+    
+   outputs = model.generate(input_ids, max_new_tokens=216)
+   tokenizer.decode(outputs[0])
+    ```
+
+## Configurations
+
+The configuration info are in `smash_config.json`.
+
+## Credits & License
+
+The license of the smashed model follows the license of the original model. Please check the license of the original model huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated before using this model which provided the base model. The license  of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
+
+## Want to compress other models?
+
+- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
+- Do it by yourself [here](https://docs.pruna.ai/en/latest/setup/pip.html).

config.json

@@ -0,0 +1,57 @@
+{
+    "_name_or_path": "/covalent/.cache/models/tmpghb8xyp_4g3cvyoc",
+    "activation_function": "silu",
+    "architectures": [
+        "ExaoneForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_exaone.ExaoneConfig",
+        "AutoModelForCausalLM": "huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated--modeling_exaone.ExaoneForCausalLM",
+        "AutoModelForSequenceClassification": "huihui-ai/EXAONE-3.5-2.4B-Instruct-abliterated--modeling_exaone.ExaoneForSequenceClassification"
+    },
+    "bos_token_id": 1,
+    "embed_dropout": 0.0,
+    "eos_token_id": 361,
+    "head_dim": 80,
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 7168,
+    "layer_norm_epsilon": 1e-05,
+    "max_position_embeddings": 32768,
+    "model_type": "exaone",
+    "num_attention_heads": 32,
+    "num_key_value_heads": 8,
+    "num_layers": 30,
+    "pad_token_id": 0,
+    "quantization_config": {
+        "_load_in_4bit": false,
+        "_load_in_8bit": true,
+        "bnb_4bit_compute_dtype": "bfloat16",
+        "bnb_4bit_quant_storage": "uint8",
+        "bnb_4bit_quant_type": "fp4",
+        "bnb_4bit_use_double_quant": false,
+        "llm_int8_enable_fp32_cpu_offload": false,
+        "llm_int8_has_fp16_weight": false,
+        "llm_int8_skip_modules": [
+            "lm_head"
+        ],
+        "llm_int8_threshold": 6.0,
+        "load_in_4bit": false,
+        "load_in_8bit": true,
+        "quant_method": "bitsandbytes"
+    },
+    "rope_scaling": {
+        "factor": 8.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "llama3"
+    },
+    "rope_theta": 1000000,
+    "torch_dtype": "float16",
+    "transformers_version": "4.46.2",
+    "use_cache": true,
+    "vocab_size": 102400,
+    "api_key": null
+}

configuration_exaone.py

@@ -0,0 +1,183 @@
+# coding=utf-8
+# Copyright 2021 The LG AI Research EXAONE Lab. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""EXAONE model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+EXAONE_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class ExaoneConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`ExaoneModel`]. It is used to
+    instantiate a EXAONE model according to the specified arguments, defining the model architecture. Instantiating a
+    configuration with the defaults will yield a similar configuration to that of the EXAONE-3.0-7.8B-Instruct [LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct)
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model
+    outputs. Read the documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 102400):
+            Vocabulary size of the EXAONE model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`ExaoneModel`]. Vocabulary size of the model.
+            Defines the different tokens that can be represented by the `inputs_ids` passed to the forward method of
+            [`ExaoneModel`].
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        hidden_size (`int`, *optional*, defaults to 2048):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
+            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        activation_function (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        embed_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
+            The epsilon used by the layer normalization layers.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if ``config.is_decoder=True``.
+        bos_token_id (`int`, *optional*, defaults to 0):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+
+    Example:
+
+    ```python
+    >>> from transformers import EXAONEModel, ExaoneConfig
+
+    >>> # Initializing a EXAONE configuration
+    >>> configuration = ExaoneConfig()
+
+    >>> # Initializing a model from configuration
+    >>> model = EXAONEModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "exaone"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    attribute_map = {"num_hidden_layers": "num_layers"}
+
+    def __init__(
+        self,
+        vocab_size=102400,
+        max_position_embeddings=2048,
+        hidden_size=2048,
+        num_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        intermediate_size=None,
+        activation_function="silu",
+        rope_theta=10000.0,
+        rope_scaling=None,
+        embed_dropout=0.0,
+        attention_dropout=0.0,
+        layer_norm_epsilon=1e-5,
+        initializer_range=0.02,
+        use_cache=True,
+        bos_token_id=0,
+        eos_token_id=2,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.num_layers = num_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_layers = num_layers
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        if intermediate_size:
+            self.intermediate_size = intermediate_size
+        else:
+            self.intermediate_size = hidden_size * 4
+        self.activation_function = activation_function
+        self.embed_dropout = embed_dropout
+        self.attention_dropout = attention_dropout
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+
+        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 361,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d524891b16b59af17bab3de3fa665bc909cf821955b28eeac4192d6932401e02
+size 2670499482

smash_config.json

@@ -0,0 +1,35 @@
+{
+    "comp_cgenerate_active": false,
+    "comp_ctranslate_active": false,
+    "comp_cwhisper_active": false,
+    "comp_diffusers2_active": false,
+    "comp_ifw_active": false,
+    "comp_onediff_active": false,
+    "comp_step_caching_active": false,
+    "comp_torch_compile_active": false,
+    "comp_ws2t_active": false,
+    "comp_x-fast_active": false,
+    "prune_torch-structured_active": false,
+    "quant_aqlm_active": false,
+    "quant_awq_active": false,
+    "quant_gptq_active": false,
+    "quant_half_active": false,
+    "quant_hqq_active": false,
+    "quant_llm-int8_active": true,
+    "quant_quanto_active": false,
+    "quant_torch_dynamic_active": false,
+    "quant_torch_static_active": false,
+    "quant_llm-int8_compute_dtype": "bfloat16",
+    "quant_llm-int8_double_quant": false,
+    "quant_llm-int8_enable_fp32_cpu_offload": false,
+    "quant_llm-int8_has_fp16_weight": false,
+    "quant_llm-int8_quant_type": "fp4",
+    "quant_llm-int8_threshold": 6.0,
+    "quant_llm-int8_weight_bits": 8,
+    "max_batch_size": 1,
+    "device": "cuda",
+    "cache_dir": "/covalent/.cache/models/tmpghb8xyp_",
+    "task": "",
+    "save_load_fn": "bitsandbytes",
+    "save_load_fn_args": {}
+}