Upload DemoRetrieverQAPipeline

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,201 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+

bloom_retriever.py

@@ -0,0 +1,38 @@
+import torch
+import numpy as np
+from transformers import FeatureExtractionPipeline
+from scipy.spatial.distance import cdist
+
+class DemoRetrieverQAPipeline(FeatureExtractionPipeline):
+    def preprocess(self, inputs, **tokenize_kwargs):
+        device = 'cuda' if torch.cuda.is_available() else 'cpu'
+        inputs = inputs.to(device)
+        self.query = inputs['question']
+        self.contexts = inputs['contexts']
+        return super().preprocess(self.query)
+
+    def _infer(self, inputs, return_tensors=False):
+        model_inputs = self.tokenizer(inputs, return_tensors=self.framework)
+        model_outputs = self.model(**model_inputs)
+        if return_tensors:
+            outputs = model_outputs[0]
+        if self.framework == "pt":
+            outputs = model_outputs[0].tolist()
+        elif self.framework == "tf":
+            outputs = model_outputs[0].numpy().tolist()
+
+        return [[ii[0][-1]] for ii in outputs]
+
+    def postprocess(self, model_outputs, return_tensors=False):
+        emb_contexts = np.concatenate([self._infer(context, return_tensors) for context in self.contexts], axis=0)
+        emb_queries = np.concatenate([self._infer(self.query, return_tensors)], axis=0)
+        # Important: take l2 distance!
+        dist = cdist(emb_queries, emb_contexts, 'euclidean')
+        top_k = lambda x: [
+            [self.contexts[qq] for qq in ii]
+            for ii in dist.argsort(axis=-1)[:,:x]
+        ]
+
+        # top 5 nearest contexts for each queries
+        top_contexts = top_k(1)
+        return {"context": top_contexts[0][0]}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "cmarkea/bloomz-3b-retriever",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "custom_pipelines": {
+    "demo-retriever-qa": {
+      "impl": "bloom_retriever.DemoRetrieverQAPipeline",
+      "pt": [
+        "AutoModel"
+      ],
+      "tf": [
+        "TFAutoModel"
+      ]
+    }
+  },
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077a11d06d66e49ee3d55275050cb97dd966108ca1fd534cdc7395ff9002745a
+size 4981821360

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3217621b737560e714ebd2513f3b3fbd5bdc93c27670118635a2e6b71eec46b9
+size 4930416288

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c579a72a62b347a1e6d3f05163a4c3e4db8032534f33a1d693d37d8acf06f94
+size 2098030608

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 12010229760
+  },
+  "weight_map": {
+    "h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.10.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.10.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.10.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.10.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.11.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.20.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.20.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.21.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.21.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.22.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.22.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.23.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.23.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.23.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.23.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.7.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "h.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.8.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.8.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.8.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.8.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "h.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "h.9.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "h.9.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.9.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "h.9.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "ln_f.bias": "model-00003-of-00003.safetensors",
+    "ln_f.weight": "model-00003-of-00003.safetensors",
+    "word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
+    "word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c875d9c9a51ccc372c8d471e1fefaac3376d8b5b840bd63eac64c16ebf6b5471
+size 14501012

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}