Upload model

README.md

@@ -1,199 +1,10 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
 ---
+## Training procedure
 
-# Model Card for Model ID
+### Framework versions
 
-<!-- Provide a quick summary of what the model is/does. -->
+- PEFT 0.5.0
 
-
-
-## 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]
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,254 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "base_model.model.model.layers.0.self_attn.q_proj",
+    "base_model.model.model.layers.0.self_attn.q_proj.lora_A.default",
+    "base_model.model.model.layers.0.self_attn.q_proj.lora_B.default",
+    "base_model.model.model.layers.0.self_attn.k_proj",
+    "base_model.model.model.layers.0.self_attn.k_proj.lora_A.default",
+    "base_model.model.model.layers.0.self_attn.k_proj.lora_B.default",
+    "base_model.model.model.layers.0.self_attn.v_proj",
+    "base_model.model.model.layers.0.self_attn.v_proj.lora_A.default",
+    "base_model.model.model.layers.0.self_attn.v_proj.lora_B.default",
+    "base_model.model.model.layers.0.self_attn.o_proj",
+    "base_model.model.model.layers.0.self_attn.o_proj.lora_A.default",
+    "base_model.model.model.layers.0.self_attn.o_proj.lora_B.default",
+    "base_model.model.model.layers.0.mlp.gate_proj",
+    "base_model.model.model.layers.0.mlp.gate_proj.lora_A.default",
+    "base_model.model.model.layers.0.mlp.gate_proj.lora_B.default",
+    "base_model.model.model.layers.0.mlp.down_proj",
+    "base_model.model.model.layers.0.mlp.up_proj",
+    "base_model.model.model.layers.1.self_attn.q_proj",
+    "base_model.model.model.layers.1.self_attn.k_proj",
+    "base_model.model.model.layers.1.self_attn.v_proj",
+    "base_model.model.model.layers.1.self_attn.o_proj",
+    "base_model.model.model.layers.1.mlp.gate_proj",
+    "base_model.model.model.layers.1.mlp.down_proj",
+    "base_model.model.model.layers.1.mlp.up_proj",
+    "base_model.model.model.layers.2.self_attn.q_proj",
+    "base_model.model.model.layers.2.self_attn.k_proj",
+    "base_model.model.model.layers.2.self_attn.v_proj",
+    "base_model.model.model.layers.2.self_attn.o_proj",
+    "base_model.model.model.layers.2.mlp.gate_proj",
+    "base_model.model.model.layers.2.mlp.down_proj",
+    "base_model.model.model.layers.2.mlp.up_proj",
+    "base_model.model.model.layers.3.self_attn.q_proj",
+    "base_model.model.model.layers.3.self_attn.k_proj",
+    "base_model.model.model.layers.3.self_attn.v_proj",
+    "base_model.model.model.layers.3.self_attn.o_proj",
+    "base_model.model.model.layers.3.mlp.gate_proj",
+    "base_model.model.model.layers.3.mlp.down_proj",
+    "base_model.model.model.layers.3.mlp.up_proj",
+    "base_model.model.model.layers.4.self_attn.q_proj",
+    "base_model.model.model.layers.4.self_attn.k_proj",
+    "base_model.model.model.layers.4.self_attn.v_proj",
+    "base_model.model.model.layers.4.self_attn.o_proj",
+    "base_model.model.model.layers.4.mlp.gate_proj",
+    "base_model.model.model.layers.4.mlp.down_proj",
+    "base_model.model.model.layers.4.mlp.up_proj",
+    "base_model.model.model.layers.5.self_attn.q_proj",
+    "base_model.model.model.layers.5.self_attn.k_proj",
+    "base_model.model.model.layers.5.self_attn.v_proj",
+    "base_model.model.model.layers.5.self_attn.o_proj",
+    "base_model.model.model.layers.5.mlp.gate_proj",
+    "base_model.model.model.layers.5.mlp.down_proj",
+    "base_model.model.model.layers.5.mlp.up_proj",
+    "base_model.model.model.layers.6.self_attn.q_proj",
+    "base_model.model.model.layers.6.self_attn.k_proj",
+    "base_model.model.model.layers.6.self_attn.v_proj",
+    "base_model.model.model.layers.6.self_attn.o_proj",
+    "base_model.model.model.layers.6.mlp.gate_proj",
+    "base_model.model.model.layers.6.mlp.down_proj",
+    "base_model.model.model.layers.6.mlp.up_proj",
+    "base_model.model.model.layers.7.self_attn.q_proj",
+    "base_model.model.model.layers.7.self_attn.k_proj",
+    "base_model.model.model.layers.7.self_attn.v_proj",
+    "base_model.model.model.layers.7.self_attn.o_proj",
+    "base_model.model.model.layers.7.mlp.gate_proj",
+    "base_model.model.model.layers.7.mlp.down_proj",
+    "base_model.model.model.layers.7.mlp.up_proj",
+    "base_model.model.model.layers.8.self_attn.q_proj",
+    "base_model.model.model.layers.8.self_attn.k_proj",
+    "base_model.model.model.layers.8.self_attn.v_proj",
+    "base_model.model.model.layers.8.self_attn.o_proj",
+    "base_model.model.model.layers.8.mlp.gate_proj",
+    "base_model.model.model.layers.8.mlp.down_proj",
+    "base_model.model.model.layers.8.mlp.up_proj",
+    "base_model.model.model.layers.9.self_attn.q_proj",
+    "base_model.model.model.layers.9.self_attn.k_proj",
+    "base_model.model.model.layers.9.self_attn.v_proj",
+    "base_model.model.model.layers.9.self_attn.o_proj",
+    "base_model.model.model.layers.9.mlp.gate_proj",
+    "base_model.model.model.layers.9.mlp.down_proj",
+    "base_model.model.model.layers.9.mlp.up_proj",
+    "base_model.model.model.layers.10.self_attn.q_proj",
+    "base_model.model.model.layers.10.self_attn.k_proj",
+    "base_model.model.model.layers.10.self_attn.v_proj",
+    "base_model.model.model.layers.10.self_attn.o_proj",
+    "base_model.model.model.layers.10.mlp.gate_proj",
+    "base_model.model.model.layers.10.mlp.down_proj",
+    "base_model.model.model.layers.10.mlp.up_proj",
+    "base_model.model.model.layers.11.self_attn.q_proj",
+    "base_model.model.model.layers.11.self_attn.k_proj",
+    "base_model.model.model.layers.11.self_attn.v_proj",
+    "base_model.model.model.layers.11.self_attn.o_proj",
+    "base_model.model.model.layers.11.mlp.gate_proj",
+    "base_model.model.model.layers.11.mlp.down_proj",
+    "base_model.model.model.layers.11.mlp.up_proj",
+    "base_model.model.model.layers.12.self_attn.q_proj",
+    "base_model.model.model.layers.12.self_attn.k_proj",
+    "base_model.model.model.layers.12.self_attn.v_proj",
+    "base_model.model.model.layers.12.self_attn.o_proj",
+    "base_model.model.model.layers.12.mlp.gate_proj",
+    "base_model.model.model.layers.12.mlp.down_proj",
+    "base_model.model.model.layers.12.mlp.up_proj",
+    "base_model.model.model.layers.13.self_attn.q_proj",
+    "base_model.model.model.layers.13.self_attn.k_proj",
+    "base_model.model.model.layers.13.self_attn.v_proj",
+    "base_model.model.model.layers.13.self_attn.o_proj",
+    "base_model.model.model.layers.13.mlp.gate_proj",
+    "base_model.model.model.layers.13.mlp.down_proj",
+    "base_model.model.model.layers.13.mlp.up_proj",
+    "base_model.model.model.layers.14.self_attn.q_proj",
+    "base_model.model.model.layers.14.self_attn.k_proj",
+    "base_model.model.model.layers.14.self_attn.v_proj",
+    "base_model.model.model.layers.14.self_attn.o_proj",
+    "base_model.model.model.layers.14.mlp.gate_proj",
+    "base_model.model.model.layers.14.mlp.down_proj",
+    "base_model.model.model.layers.14.mlp.up_proj",
+    "base_model.model.model.layers.15.self_attn.q_proj",
+    "base_model.model.model.layers.15.self_attn.k_proj",
+    "base_model.model.model.layers.15.self_attn.v_proj",
+    "base_model.model.model.layers.15.self_attn.o_proj",
+    "base_model.model.model.layers.15.mlp.gate_proj",
+    "base_model.model.model.layers.15.mlp.down_proj",
+    "base_model.model.model.layers.15.mlp.up_proj",
+    "base_model.model.model.layers.16.self_attn.q_proj",
+    "base_model.model.model.layers.16.self_attn.k_proj",
+    "base_model.model.model.layers.16.self_attn.v_proj",
+    "base_model.model.model.layers.16.self_attn.o_proj",
+    "base_model.model.model.layers.16.mlp.gate_proj",
+    "base_model.model.model.layers.16.mlp.down_proj",
+    "base_model.model.model.layers.16.mlp.up_proj",
+    "base_model.model.model.layers.17.self_attn.q_proj",
+    "base_model.model.model.layers.17.self_attn.k_proj",
+    "base_model.model.model.layers.17.self_attn.v_proj",
+    "base_model.model.model.layers.17.self_attn.o_proj",
+    "base_model.model.model.layers.17.mlp.gate_proj",
+    "base_model.model.model.layers.17.mlp.down_proj",
+    "base_model.model.model.layers.17.mlp.up_proj",
+    "base_model.model.model.layers.18.self_attn.q_proj",
+    "base_model.model.model.layers.18.self_attn.k_proj",
+    "base_model.model.model.layers.18.self_attn.v_proj",
+    "base_model.model.model.layers.18.self_attn.o_proj",
+    "base_model.model.model.layers.18.mlp.gate_proj",
+    "base_model.model.model.layers.18.mlp.down_proj",
+    "base_model.model.model.layers.18.mlp.up_proj",
+    "base_model.model.model.layers.19.self_attn.q_proj",
+    "base_model.model.model.layers.19.self_attn.k_proj",
+    "base_model.model.model.layers.19.self_attn.v_proj",
+    "base_model.model.model.layers.19.self_attn.o_proj",
+    "base_model.model.model.layers.19.mlp.gate_proj",
+    "base_model.model.model.layers.19.mlp.down_proj",
+    "base_model.model.model.layers.19.mlp.up_proj",
+    "base_model.model.model.layers.20.self_attn.q_proj",
+    "base_model.model.model.layers.20.self_attn.k_proj",
+    "base_model.model.model.layers.20.self_attn.v_proj",
+    "base_model.model.model.layers.20.self_attn.o_proj",
+    "base_model.model.model.layers.20.mlp.gate_proj",
+    "base_model.model.model.layers.20.mlp.down_proj",
+    "base_model.model.model.layers.20.mlp.up_proj",
+    "base_model.model.model.layers.21.self_attn.q_proj",
+    "base_model.model.model.layers.21.self_attn.k_proj",
+    "base_model.model.model.layers.21.self_attn.v_proj",
+    "base_model.model.model.layers.21.self_attn.o_proj",
+    "base_model.model.model.layers.21.mlp.gate_proj",
+    "base_model.model.model.layers.21.mlp.down_proj",
+    "base_model.model.model.layers.21.mlp.up_proj",
+    "base_model.model.model.layers.22.self_attn.q_proj",
+    "base_model.model.model.layers.22.self_attn.k_proj",
+    "base_model.model.model.layers.22.self_attn.v_proj",
+    "base_model.model.model.layers.22.self_attn.o_proj",
+    "base_model.model.model.layers.22.mlp.gate_proj",
+    "base_model.model.model.layers.22.mlp.down_proj",
+    "base_model.model.model.layers.22.mlp.up_proj",
+    "base_model.model.model.layers.23.self_attn.q_proj",
+    "base_model.model.model.layers.23.self_attn.k_proj",
+    "base_model.model.model.layers.23.self_attn.v_proj",
+    "base_model.model.model.layers.23.self_attn.o_proj",
+    "base_model.model.model.layers.23.mlp.gate_proj",
+    "base_model.model.model.layers.23.mlp.down_proj",
+    "base_model.model.model.layers.23.mlp.up_proj",
+    "base_model.model.model.layers.24.self_attn.q_proj",
+    "base_model.model.model.layers.24.self_attn.k_proj",
+    "base_model.model.model.layers.24.self_attn.v_proj",
+    "base_model.model.model.layers.24.self_attn.o_proj",
+    "base_model.model.model.layers.24.mlp.gate_proj",
+    "base_model.model.model.layers.24.mlp.down_proj",
+    "base_model.model.model.layers.24.mlp.up_proj",
+    "base_model.model.model.layers.25.self_attn.q_proj",
+    "base_model.model.model.layers.25.self_attn.k_proj",
+    "base_model.model.model.layers.25.self_attn.v_proj",
+    "base_model.model.model.layers.25.self_attn.o_proj",
+    "base_model.model.model.layers.25.mlp.gate_proj",
+    "base_model.model.model.layers.25.mlp.down_proj",
+    "base_model.model.model.layers.25.mlp.up_proj",
+    "base_model.model.model.layers.26.self_attn.q_proj",
+    "base_model.model.model.layers.26.self_attn.k_proj",
+    "base_model.model.model.layers.26.self_attn.v_proj",
+    "base_model.model.model.layers.26.self_attn.o_proj",
+    "base_model.model.model.layers.26.mlp.gate_proj",
+    "base_model.model.model.layers.26.mlp.down_proj",
+    "base_model.model.model.layers.26.mlp.up_proj",
+    "base_model.model.model.layers.27.self_attn.q_proj",
+    "base_model.model.model.layers.27.self_attn.k_proj",
+    "base_model.model.model.layers.27.self_attn.v_proj",
+    "base_model.model.model.layers.27.self_attn.o_proj",
+    "base_model.model.model.layers.27.mlp.gate_proj",
+    "base_model.model.model.layers.27.mlp.down_proj",
+    "base_model.model.model.layers.27.mlp.up_proj",
+    "base_model.model.model.layers.28.self_attn.q_proj",
+    "base_model.model.model.layers.28.self_attn.k_proj",
+    "base_model.model.model.layers.28.self_attn.v_proj",
+    "base_model.model.model.layers.28.self_attn.o_proj",
+    "base_model.model.model.layers.28.mlp.gate_proj",
+    "base_model.model.model.layers.28.mlp.down_proj",
+    "base_model.model.model.layers.28.mlp.up_proj",
+    "base_model.model.model.layers.29.self_attn.q_proj",
+    "base_model.model.model.layers.29.self_attn.k_proj",
+    "base_model.model.model.layers.29.self_attn.v_proj",
+    "base_model.model.model.layers.29.self_attn.o_proj",
+    "base_model.model.model.layers.29.mlp.gate_proj",
+    "base_model.model.model.layers.29.mlp.down_proj",
+    "base_model.model.model.layers.29.mlp.up_proj",
+    "base_model.model.model.layers.30.self_attn.q_proj",
+    "base_model.model.model.layers.30.self_attn.k_proj",
+    "base_model.model.model.layers.30.self_attn.v_proj",
+    "base_model.model.model.layers.30.self_attn.o_proj",
+    "base_model.model.model.layers.30.mlp.gate_proj",
+    "base_model.model.model.layers.30.mlp.down_proj",
+    "base_model.model.model.layers.30.mlp.up_proj",
+    "base_model.model.model.layers.31.self_attn.q_proj",
+    "base_model.model.model.layers.31.self_attn.k_proj",
+    "base_model.model.model.layers.31.self_attn.v_proj",
+    "base_model.model.model.layers.31.self_attn.o_proj",
+    "base_model.model.model.layers.31.mlp.gate_proj",
+    "base_model.model.model.layers.31.mlp.down_proj",
+    "base_model.model.model.layers.31.mlp.up_proj",
+    "base_model.model.lm_head"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036d3a36fd94a768446e6a29d0e851384b906f022de296f9c31ec65daf2b028c
+size 165462050