Upload 12 files

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconModel"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
+  },
+  "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,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 65024
+}

loftq_init/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: tiiuae/falcon-7b
+---
+
+# 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. -->
+
+
+
+- **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]
+
+
+### Framework versions
+
+- PEFT 0.10.0

loftq_init/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model_zoo/loftq/falcon-7b-4bit-32rank",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {
+    "loftq_bits": 4,
+    "loftq_iter": 5
+  },
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_4h_to_h",
+    "dense_h_to_4h",
+    "dense",
+    "query_key_value"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

loftq_init/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f0e185540ff3c6eae801b193ff36c1040a06c0e3c466cd049d633bb0fd8a91
+size 130635594

loftq_init/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491ee7bb216bc34590bcb6536cd18bbe5b32bb8ae7b916d59cc6b55e136425af
+size 130581096

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7135ab65310e9ba94974c0a2a9551136b38004866b6f39069207394959c863
+size 4981285080

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9872451996ab6f976ed5affb832751dbdd541f0cf6447d5899ff5ded81e4264
+size 4969689704

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3443e83a1969f29c3f91778b3ddd484804c4771d1503535ae97c2c0f6d1c7f3
+size 3892487592

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 13843441408
+  },
+  "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.weight": "model-00001-of-00003.safetensors",
+    "h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.0.self_attention.dense.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.1.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.10.self_attention.query_key_value.weight": "model-00001-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.weight": "model-00002-of-00003.safetensors",
+    "h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.11.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.12.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.13.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.14.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.15.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.16.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.17.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.18.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.19.self_attention.dense.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.2.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.20.self_attention.dense.weight": "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.weight": "model-00002-of-00003.safetensors",
+    "h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "h.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.23.input_layernorm.weight": "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.weight": "model-00003-of-00003.safetensors",
+    "h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.23.self_attention.query_key_value.weight": "model-00003-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.weight": "model-00003-of-00003.safetensors",
+    "h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.24.self_attention.dense.weight": "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.weight": "model-00003-of-00003.safetensors",
+    "h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.25.self_attention.dense.weight": "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.weight": "model-00003-of-00003.safetensors",
+    "h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.26.self_attention.dense.weight": "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.weight": "model-00003-of-00003.safetensors",
+    "h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.27.self_attention.dense.weight": "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.weight": "model-00003-of-00003.safetensors",
+    "h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.28.self_attention.dense.weight": "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.weight": "model-00003-of-00003.safetensors",
+    "h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.29.self_attention.dense.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.30.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.30.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "h.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "h.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "h.31.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "h.31.self_attention.query_key_value.weight": "model-00003-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.weight": "model-00001-of-00003.safetensors",
+    "h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.4.self_attention.dense.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.5.self_attention.dense.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.6.self_attention.dense.weight": "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.weight": "model-00001-of-00003.safetensors",
+    "h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "h.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "h.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "h.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "h.9.self_attention.query_key_value.weight": "model-00001-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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,123 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "task_type": "feature_extraction",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}