初始化项目，由ModelHub XC社区提供模型

Model: vilsonrodrigues/falcon-7b-instruct-sharded Source: Original Platform
2026-09-04 02:08:19 +08:00
commit 065a0fcecd
26 changed files with 131977 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,236 @@
+---
+datasets:
+  - tiiuae/falcon-refinedweb
+language:
+  - en
+inference: true
+widget:
+  - text: "Hey Falcon! Any recommendations for my holidays in Abu Dhabi?"
+    example_title: "Abu Dhabi Trip"
+  - text: "What's the Everett interpretation of quantum mechanics?"
+    example_title: "Q/A: Quantum & Answers"
+  - text: "Give me a list of the top 10 dive sites you would recommend around the world."
+    example_title: "Diving Top 10"
+  - text: "Can you tell me more about deep-water soloing?"
+    example_title: "Extreme sports"
+  - text: "Can you write a short tweet about the Apache 2.0 release of our latest AI model, Falcon LLM?"
+    example_title: "Twitter Helper"
+  - text: "What are the responsabilities of a Chief Llama Officer?"
+    example_title: "Trendy Jobs"
+license: apache-2.0
+---
+
+# Resharded
+
+Resharded version of https://huggingface.co/tiiuae/falcon-7b-instruct for low RAM enviroments (e.g. Colab, Kaggle) in safetensors
+
+Tutorial: https://medium.com/@vilsonrodrigues/run-your-private-llm-falcon-7b-instruct-with-less-than-6gb-of-gpu-using-4-bit-quantization-ff1d4ffbabcc
+
+---
+
+
+# ✨ Falcon-7B-Instruct
+
+**Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license.**
+
+*Paper coming soon 😊.*
+
+🤗 To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)!
+
+## Why use Falcon-7B-Instruct?
+
+* **You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).**
+* **Falcon-7B is a strong base model, outperforming comparable open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
+* **It features an architecture optimized for inference**, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)). 
+
+⚠️ Falcon is now available as a core model in the `transformers` library! To use the in-library version, please install the latest version of `transformers` with `pip install git+https://github.com/ huggingface/transformers.git`, then simply remove the `trust_remote_code=True` argument from `from_pretrained()`.
+
+💬 **This is an instruct model, which may not be ideal for further finetuning.** If you are interested in building your own instruct/chat model, we recommend starting from [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b). 
+
+🔥 **Looking for an even more powerful model?** [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) is Falcon-7B-Instruct's big brother!
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
+model = "tiiuae/falcon-7b-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+sequences = pipeline(
+   "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
+    max_length=200,
+    do_sample=True,
+    top_k=10,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```
+
+💥 **Falcon LLMs require PyTorch 2.0 for use with `transformers`!**
+
+For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon). 
+
+You will need **at least 16GB of memory** to swiftly run inference with Falcon-7B-Instruct.
+
+
+# Model Card for Falcon-7B-Instruct
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** [https://www.tii.ae](https://www.tii.ae);
+- **Model type:** Causal decoder-only;
+- **Language(s) (NLP):** English and French;
+- **License:** Apache 2.0;
+- **Finetuned from model:** [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).
+
+### Model Source
+
+- **Paper:** *coming soon*.
+
+## Uses
+
+### Direct Use
+
+Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets.
+
+### Out-of-Scope Use
+
+Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful. 
+
+## Bias, Risks, and Limitations
+
+Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
+
+### Recommendations
+
+We recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use.
+
+## How to Get Started with the Model
+
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
+model = "tiiuae/falcon-7b-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+sequences = pipeline(
+   "Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
+    max_length=200,
+    do_sample=True,
+    top_k=10,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```
+
+## Training Details
+
+### Training Data
+
+Falcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets.
+
+| **Data source**    | **Fraction** | **Tokens** | **Description**                       |
+|--------------------|--------------|------------|-----------------------------------|
+| [Bai ze](https://github.com/project-baize/baize-chatbot) | 65%          | 164M     | chat                 |
+| [GPT4All](https://github.com/nomic-ai/gpt4all)              | 25%           | 62M       | instruct                                  |
+| [GPTeacher](https://github.com/teknium1/GPTeacher)      | 5%           | 11M        | instruct |
+| [RefinedWeb-English](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) | 5%          | 13M     | massive web crawl                 |
+
+
+The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) tokenizer.
+
+
+## Evaluation
+
+*Paper coming soon.*
+
+See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results.
+
+Note that this model variant is not optimized for NLP benchmarks. 
+
+
+## Technical Specifications 
+
+For more information about pretraining, see [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).
+
+### Model Architecture and Objective
+
+Falcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
+
+The architecture is broadly adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), with the following differences:
+
+* **Positionnal embeddings:** rotary ([Su et al., 2021](https://arxiv.org/abs/2104.09864));
+* **Attention:** multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135));
+* **Decoder-block:** parallel attention/MLP with a single layer norm.
+
+| **Hyperparameter** | **Value** | **Comment**                            |
+|--------------------|-----------|----------------------------------------|
+| Layers             | 32        |                                        |
+| `d_model`          | 4544      | Increased to compensate for multiquery                                       |
+| `head_dim`         | 64        | Reduced to optimise for FlashAttention |
+| Vocabulary         | 65024     |                                        |
+| Sequence length    | 2048      |                                        |
+
+### Compute Infrastructure
+
+#### Hardware
+
+Falcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances. 
+
+#### Software
+
+Falcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)
+
+
+## Citation
+
+*Paper coming soon* 😊. In the meanwhile, you can use the following information to cite: 
+```
+@article{falcon40b,
+  title={{Falcon-40B}: an open large language model with state-of-the-art performance},
+  author={Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme},
+  year={2023}
+}
+```
+
+To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](https://arxiv.org/abs/2306.01116).
+
+```
+@article{refinedweb,
+  title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
+  author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
+  journal={arXiv preprint arXiv:2306.01116},
+  eprint={2306.01116},
+  eprinttype = {arXiv},
+  url={https://arxiv.org/abs/2306.01116},
+  year={2023}
+}
+```
+
+
+## License
+
+Falcon-7B-Instruct is made available under the Apache 2.0 license.
+
+## Contact
+falconllm@tii.ae
--- a/config.json
+++ b/config.json
@@ -0,0 +1,33 @@
+{
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_falcon.FalconConfig",
+    "AutoModel": "modeling_falcon.FalconModel",
+    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
+    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 65024
+}
--- a/configuration_falcon.py
+++ b/configuration_falcon.py
@@ -0,0 +1,147 @@
+# coding=utf-8
+# Copyright 2023 the Falcon authors and HuggingFace Inc. team.  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.
+""" Falcon configuration"""
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+FALCON_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "tiiuae/falcon-40b": "https://huggingface.co/tiiuae/falcon-40b/resolve/main/config.json",
+    "tiiuae/falcon-7b": "https://huggingface.co/tiiuae/falcon-7b/resolve/main/config.json",
+}
+
+
+class FalconConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`FalconModel`]. It is used to instantiate a Falcon
+    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
+    [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) architecture.
+
+    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 65024):
+            Vocabulary size of the Falcon model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`FalconModel`]
+        hidden_size (`int`, *optional*, defaults to 4544):
+            Dimension of the hidden representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 71):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        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 the model should return the last key/values attentions (not used by all models). Only relevant if
+            `config.is_decoder=True`.
+        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
+            The epsilon used by the layer normalization layers.
+        hidden_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probability for MLP layers.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probability for attention layers.
+        num_kv_heads (`int`, *optional*):
+            Number of key-value heads to use per attention layer. If unset, defaults to the same value as
+            `num_attention_heads`.
+        alibi (`bool`, *optional*, defaults to `False`):
+            Whether to use ALiBi positional biases during self-attention.
+        new_decoder_architecture (`bool`, *optional*, defaults to `False`):
+            Whether to use the new (Falcon-40B) decoder architecture. If `True`, the `multi_query` and `parallel_attn`
+            arguments are ignored, as the new decoder always uses parallel attention.
+        multi_query (`bool`, *optional*, defaults to `True`):
+            Whether to use multi-query attention in the decoder. Ignored when `new_decoder_architecture` is `True`.
+        parallel_attn (`bool`, *optional*, defaults to `True`):
+            Whether to compute attention in parallel with the feedforward layer. If False, they are consecutive
+            instead, as in the original Transformer architecture. Ignored when `new_decoder_architecture` is `True`.
+        bias (`bool`, *optional*, defaults to `False`):
+            Whether to use bias on Linear layers.
+        bos_token_id (`int`, *optional*, defaults to 11):
+            The id of the "beginning-of-sequence" token.
+        eos_token_id (`int`, *optional*, defaults to 11):
+            The id of the "end-of-sequence" token.
+
+    Example:
+
+    ```python
+    >>> from transformers import FalconModel, FalconConfig
+
+    >>> # Initializing a small (2-layer) Falcon configuration
+    >>> configuration = FalconConfig(num_hidden_layers=2)
+
+    >>> # Initializing a model from the small configuration
+    >>> model = FalconModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+    model_type = "falcon"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=65024,
+        hidden_size=4544,
+        num_hidden_layers=32,
+        num_attention_heads=71,
+        layer_norm_epsilon=1e-5,
+        initializer_range=0.02,
+        use_cache=True,
+        hidden_dropout=0.0,
+        attention_dropout=0.0,
+        num_kv_heads=None,
+        alibi=False,
+        new_decoder_architecture=False,
+        multi_query=True,
+        parallel_attn=True,
+        bias=False,
+        bos_token_id=11,
+        eos_token_id=11,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        # Backward compatibility with n_embed kwarg
+        n_embed = kwargs.pop("n_embed", None)
+        self.hidden_size = hidden_size if n_embed is None else n_embed
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range
+        self.use_cache = use_cache
+        self.hidden_dropout = hidden_dropout
+        self.attention_dropout = attention_dropout
+
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+        self.num_kv_heads = num_attention_heads if num_kv_heads is None else num_kv_heads
+        self.alibi = alibi
+        self.new_decoder_architecture = new_decoder_architecture
+        self.multi_query = multi_query  # Ignored when new_decoder_architecture is True
+        self.parallel_attn = parallel_attn
+        self.bias = bias
+
+        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
+
+    @property
+    def head_dim(self):
+        return self.hidden_size // self.num_attention_heads
+
+    @property
+    def rotary(self):
+        return not self.alibi
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.31.0.dev0"
+}
--- a/handler.py
+++ b/handler.py
@@ -0,0 +1,33 @@
+import torch
+
+from typing import Any, Dict
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load model and tokenizer from path
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+        self.model = AutoModelForCausalLM.from_pretrained(
+            path, device_map="auto", torch_dtype=torch.float16, trust_remote_code=True
+        )
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
+        # process input
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # preprocess
+        inputs = self.tokenizer(inputs, return_tensors="pt").to(self.device)
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            outputs = self.model.generate(**inputs, **parameters)
+        else:
+            outputs = self.model.generate(**inputs)
+
+        # postprocess the prediction
+        prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        return [{"generated_text": prediction}]
--- a/model-00001-of-00015.safetensors
+++ b/model-00001-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22b2c7425abdcbf2d50986e209ac2f8b73afcbcd0e555a9299bf6e52ebe566a
+size 1679790280
--- a/model-00002-of-00015.safetensors
+++ b/model-00002-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd862f6b8aeeff3735ea53b01c26e305053edee6dc2df16bf857c5da2d53fbc9
+size 1986965752
--- a/model-00003-of-00015.safetensors
+++ b/model-00003-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23536f2859f4bee312ff856b40ce6d9a209eee231fa3bf4667a2e7deb72d77b1
+size 1824072352
--- a/model-00004-of-00015.safetensors
+++ b/model-00004-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cafba110ff037d261ba5f25976c210cb42877049834afd4ba1b64f111919af7
+size 1986929176
--- a/model-00005-of-00015.safetensors
+++ b/model-00005-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5338841ea89a57f1ab3492acb04f6a590e602398cb5cb857551945b0b8a4533c
+size 1986965736
--- a/model-00006-of-00015.safetensors
+++ b/model-00006-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fd9e1c3db0a402798983e5faca15f3396de00c33226aeb82cd7f1bbd07536b
+size 1824072368
--- a/model-00007-of-00015.safetensors
+++ b/model-00007-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b1bb55ce01a5a4f6f5a6d6656ee0798e94b0ddc6f52218a09e7d6614a162e6
+size 1986929192
--- a/model-00008-of-00015.safetensors
+++ b/model-00008-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede083616580619f8e37b6ebd3756c701930a3fc4a9df59bcf3c79b07c4e1bf4
+size 1986965768
--- a/model-00009-of-00015.safetensors
+++ b/model-00009-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087911a79378d63e6ac4a199d13aeac8947d00020a870e710db9d1a8ea4bdebf
+size 1824072368
--- a/model-00010-of-00015.safetensors
+++ b/model-00010-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebda63ca06ccf6b9e3809dc69632a242124e44cb9e07a8d3b3356dd4dcd4840d
+size 1986929192
--- a/model-00011-of-00015.safetensors
+++ b/model-00011-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fb1dbfc84b48ec1e628f856cb3f30531bd80600470f0f55a47cb10f1aaa7ba
+size 1986965768
--- a/model-00012-of-00015.safetensors
+++ b/model-00012-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fc371f7c0100dc1d6fda58dff9bb7d41ad65062efda4f8ace211f3b4f59c80
+size 1824072368
--- a/model-00013-of-00015.safetensors
+++ b/model-00013-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873d3635e8060d94e85d449b494c4c6644c10de758e928891f349f5da348b7ed
+size 1986929192
--- a/model-00014-of-00015.safetensors
+++ b/model-00014-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8c1dac7869ec25c370c13ef8b81fe8168b7f8614e1452d6eb37d65d3ec20d8
+size 1986965768
--- a/model-00015-of-00015.safetensors
+++ b/model-00015-of-00015.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8020319f796ff381158c3c293271cf30f8c70bf2af68ca88750feb8778c01d52
+size 828281024
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 27686882816
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00015.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00002-of-00015.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00005-of-00015.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00006-of-00015.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00006-of-00015.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00007-of-00015.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00007-of-00015.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00008-of-00015.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00008-of-00015.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00008-of-00015.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00009-of-00015.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00009-of-00015.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00002-of-00015.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00010-of-00015.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00010-of-00015.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00011-of-00015.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00011-of-00015.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00011-of-00015.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00012-of-00015.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00012-of-00015.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00013-of-00015.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00013-of-00015.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00014-of-00015.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00002-of-00015.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.30.input_layernorm.bias": "model-00014-of-00015.safetensors",
+    "transformer.h.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.31.input_layernorm.bias": "model-00014-of-00015.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00015-of-00015.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00015-of-00015.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00015-of-00015.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00015-of-00015.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00003-of-00015.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00003-of-00015.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00004-of-00015.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00004-of-00015.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00005-of-00015.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00005-of-00015.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+    "transformer.ln_f.bias": "model-00015-of-00015.safetensors",
+    "transformer.ln_f.weight": "model-00015-of-00015.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00015.safetensors"
+  }
+}
--- a/modeling_falcon.py
+++ b/modeling_falcon.py
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>"
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "name_or_path": "tiiuae/falcon_tokenizer",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}