Перевод на FastAPI POST API

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/capybara_fas_ai.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.9 (github_api_test)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,34 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Annotator" enabled="false" level="ERROR" enabled_by_default="false" />
+    <inspection_tool class="EditorConfigRootDeclarationUniqueness" enabled="false" level="ERROR" enabled_by_default="false" />
+    <inspection_tool class="PyCompatibilityInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ourVersions">
+        <value>
+          <list size="1">
+            <item index="0" class="java.lang.String" itemvalue="3.13" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="10">
+            <item index="0" class="java.lang.String" itemvalue="httpx" />
+            <item index="1" class="java.lang.String" itemvalue="pydantic" />
+            <item index="2" class="java.lang.String" itemvalue="aiogram" />
+            <item index="3" class="java.lang.String" itemvalue="psycopg2-binary" />
+            <item index="4" class="java.lang.String" itemvalue="python-dotenv" />
+            <item index="5" class="java.lang.String" itemvalue="pillow" />
+            <item index="6" class="java.lang.String" itemvalue="aiohttp" />
+            <item index="7" class="java.lang.String" itemvalue="python-multipart" />
+            <item index="8" class="java.lang.String" itemvalue="gunicorn" />
+            <item index="9" class="java.lang.String" itemvalue="django-formtools" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.9 (github_api_test)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (github_api_test)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/capybara_fas_ai.iml" filepath="$PROJECT_DIR$/.idea/capybara_fas_ai.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

README.md

@@ -1,14 +1,202 @@
 ---
-title: Capybara Fas Ai
-emoji: 🏃
-colorFrom: blue
-colorTo: green
-sdk: gradio
-sdk_version: 5.25.0
-app_file: app.py
-pinned: false
-license: other
-short_description: my_ai_1
+base_model: NousResearch/Nous-Capybara-3B-V1.9
+library_name: peft
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 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 0.14.0

app.py

@@ -0,0 +1,37 @@
+# app.py
+import os
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+hf_token = os.getenv("HF_TOKEN")
+model_path = "./capybara-finetuned"  # локальная модель или путь на Hugging Face
+
+tokenizer = AutoTokenizer.from_pretrained(
+    model_path,
+    token=hf_token,
+    trust_remote_code=True,
+    use_fast=False,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    token=hf_token,
+    device_map="auto",
+    torch_dtype="auto",
+    trust_remote_code=True
+)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+app = FastAPI()
+
+class Input(BaseModel):
+    text: str
+
+@app.post("/classify")
+async def classify(input: Input):
+    prompt = f"### Вопрос:\n{input.text}\n\n### Класс:"
+    output = pipe(prompt, max_new_tokens=10, do_sample=False)[0]["generated_text"]
+    label = output.split("### Класс:")[-1].strip().split()[0].lower()
+    return {"label": label}

capybara-finetuned/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Nous-Capybara-3B-V1.9
+library_name: peft
+---
+
+# 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 0.14.0

capybara-finetuned/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Capybara-3B-V1.9",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

capybara-finetuned/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3e58810019f8c2423473124d01849395572ed748ab106aff696e68fe511594
+size 41977424

capybara-finetuned/checkpoint-193/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Nous-Capybara-3B-V1.9
+library_name: peft
+---
+
+# 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 0.14.0

capybara-finetuned/checkpoint-193/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Capybara-3B-V1.9",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

capybara-finetuned/checkpoint-193/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1cffa05984bb9ec4cccf6fe24b4fa1e2f160a679abffee220de9914bf0b4f4
+size 41977424

capybara-finetuned/checkpoint-193/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5346d830853d3585860a55a744ab7368789f3985ea18232bd4fc69de13e474
+size 84100858

capybara-finetuned/checkpoint-193/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5875d8cc785fd3e6c6b01f2be69f2dcb4892851d4e48f50fde2b99e161c32ac5
+size 14244

capybara-finetuned/checkpoint-193/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83b6a26d96339cdb88224ae8d6de87f5142e8f652dddb69b9d2ad537cd43ce1
+size 988

capybara-finetuned/checkpoint-193/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df4562b25749970667ca99578444d9238c0f6469c2aeca8d78f2e9cb3094c36
+size 1064

capybara-finetuned/checkpoint-193/trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 193,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05181347150259067,
+      "grad_norm": 0.8095124363899231,
+      "learning_rate": 0.00019792746113989637,
+      "loss": 12.3719,
+      "step": 10
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.2720714509487152,
+      "learning_rate": 0.00019447322970639035,
+      "loss": 0.2877,
+      "step": 20
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 0.3335513770580292,
+      "learning_rate": 0.0001910189982728843,
+      "loss": 0.3723,
+      "step": 30
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.21196776628494263,
+      "learning_rate": 0.00018756476683937825,
+      "loss": 0.1598,
+      "step": 40
+    },
+    {
+      "epoch": 0.25906735751295334,
+      "grad_norm": 0.41250184178352356,
+      "learning_rate": 0.0001841105354058722,
+      "loss": 0.1899,
+      "step": 50
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.2743557095527649,
+      "learning_rate": 0.00018065630397236614,
+      "loss": 0.3541,
+      "step": 60
+    },
+    {
+      "epoch": 0.3626943005181347,
+      "grad_norm": 0.28188714385032654,
+      "learning_rate": 0.00017720207253886012,
+      "loss": 0.1689,
+      "step": 70
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.3063858151435852,
+      "learning_rate": 0.00017374784110535407,
+      "loss": 0.2957,
+      "step": 80
+    },
+    {
+      "epoch": 0.46632124352331605,
+      "grad_norm": 0.24155083298683167,
+      "learning_rate": 0.00017029360967184802,
+      "loss": 0.2411,
+      "step": 90
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.3580751121044159,
+      "learning_rate": 0.00016683937823834197,
+      "loss": 0.2035,
+      "step": 100
+    },
+    {
+      "epoch": 0.5699481865284974,
+      "grad_norm": 0.32368239760398865,
+      "learning_rate": 0.00016338514680483594,
+      "loss": 0.2863,
+      "step": 110
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 0.31771329045295715,
+      "learning_rate": 0.0001599309153713299,
+      "loss": 0.2815,
+      "step": 120
+    },
+    {
+      "epoch": 0.6735751295336787,
+      "grad_norm": 0.1532900333404541,
+      "learning_rate": 0.00015647668393782384,
+      "loss": 0.1949,
+      "step": 130
+    },
+    {
+      "epoch": 0.7253886010362695,
+      "grad_norm": 0.41243669390678406,
+      "learning_rate": 0.0001530224525043178,
+      "loss": 0.1595,
+      "step": 140
+    },
+    {
+      "epoch": 0.7772020725388601,
+      "grad_norm": 0.10424460470676422,
+      "learning_rate": 0.00014956822107081174,
+      "loss": 0.1694,
+      "step": 150
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 0.2025623470544815,
+      "learning_rate": 0.0001461139896373057,
+      "loss": 0.2369,
+      "step": 160
+    },
+    {
+      "epoch": 0.8808290155440415,
+      "grad_norm": 0.1760733723640442,
+      "learning_rate": 0.00014265975820379966,
+      "loss": 0.3239,
+      "step": 170
+    },
+    {
+      "epoch": 0.9326424870466321,
+      "grad_norm": 0.10223771631717682,
+      "learning_rate": 0.0001392055267702936,
+      "loss": 0.1242,
+      "step": 180
+    },
+    {
+      "epoch": 0.9844559585492227,
+      "grad_norm": 0.4485471844673157,
+      "learning_rate": 0.00013575129533678756,
+      "loss": 0.3755,
+      "step": 190
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 579,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3174543906570240.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

capybara-finetuned/checkpoint-193/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
+size 5304

capybara-finetuned/checkpoint-386/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Nous-Capybara-3B-V1.9
+library_name: peft
+---
+
+# 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 0.14.0

capybara-finetuned/checkpoint-386/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Capybara-3B-V1.9",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

capybara-finetuned/checkpoint-386/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c48baf1611005f53c51a539c229cfaf642e73bf8e0bd31de3a6fdc5137c2bf4
+size 41977424

capybara-finetuned/checkpoint-386/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7ae2f56bbb3d9d1eddcce3fe03c531162565f3bf8fade6f62694e71b727cdd
+size 84100858

capybara-finetuned/checkpoint-386/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe550639dad04133d303c68a9bec2bc782de93b44e018edd8ecc0eb84989821
+size 14244

capybara-finetuned/checkpoint-386/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280ca9c9355adf4466a41f2ee36bbca8aa427ac79a7ddbfe9392315c33de41ad
+size 988

capybara-finetuned/checkpoint-386/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b59b3a2a0fed8bd1d0e2c1ff88569235401e51bccb1720c6a789060b38d11fd
+size 1064

capybara-finetuned/checkpoint-386/trainer_state.json

@@ -0,0 +1,300 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 386,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05181347150259067,
+      "grad_norm": 0.8095124363899231,
+      "learning_rate": 0.00019792746113989637,
+      "loss": 12.3719,
+      "step": 10
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.2720714509487152,
+      "learning_rate": 0.00019447322970639035,
+      "loss": 0.2877,
+      "step": 20
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 0.3335513770580292,
+      "learning_rate": 0.0001910189982728843,
+      "loss": 0.3723,
+      "step": 30
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.21196776628494263,
+      "learning_rate": 0.00018756476683937825,
+      "loss": 0.1598,
+      "step": 40
+    },
+    {
+      "epoch": 0.25906735751295334,
+      "grad_norm": 0.41250184178352356,
+      "learning_rate": 0.0001841105354058722,
+      "loss": 0.1899,
+      "step": 50
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.2743557095527649,
+      "learning_rate": 0.00018065630397236614,
+      "loss": 0.3541,
+      "step": 60
+    },
+    {
+      "epoch": 0.3626943005181347,
+      "grad_norm": 0.28188714385032654,
+      "learning_rate": 0.00017720207253886012,
+      "loss": 0.1689,
+      "step": 70
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.3063858151435852,
+      "learning_rate": 0.00017374784110535407,
+      "loss": 0.2957,
+      "step": 80
+    },
+    {
+      "epoch": 0.46632124352331605,
+      "grad_norm": 0.24155083298683167,
+      "learning_rate": 0.00017029360967184802,
+      "loss": 0.2411,
+      "step": 90
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.3580751121044159,
+      "learning_rate": 0.00016683937823834197,
+      "loss": 0.2035,
+      "step": 100
+    },
+    {
+      "epoch": 0.5699481865284974,
+      "grad_norm": 0.32368239760398865,
+      "learning_rate": 0.00016338514680483594,
+      "loss": 0.2863,
+      "step": 110
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 0.31771329045295715,
+      "learning_rate": 0.0001599309153713299,
+      "loss": 0.2815,
+      "step": 120
+    },
+    {
+      "epoch": 0.6735751295336787,
+      "grad_norm": 0.1532900333404541,
+      "learning_rate": 0.00015647668393782384,
+      "loss": 0.1949,
+      "step": 130
+    },
+    {
+      "epoch": 0.7253886010362695,
+      "grad_norm": 0.41243669390678406,
+      "learning_rate": 0.0001530224525043178,
+      "loss": 0.1595,
+      "step": 140
+    },
+    {
+      "epoch": 0.7772020725388601,
+      "grad_norm": 0.10424460470676422,
+      "learning_rate": 0.00014956822107081174,
+      "loss": 0.1694,
+      "step": 150
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 0.2025623470544815,
+      "learning_rate": 0.0001461139896373057,
+      "loss": 0.2369,
+      "step": 160
+    },
+    {
+      "epoch": 0.8808290155440415,
+      "grad_norm": 0.1760733723640442,
+      "learning_rate": 0.00014265975820379966,
+      "loss": 0.3239,
+      "step": 170
+    },
+    {
+      "epoch": 0.9326424870466321,
+      "grad_norm": 0.10223771631717682,
+      "learning_rate": 0.0001392055267702936,
+      "loss": 0.1242,
+      "step": 180
+    },
+    {
+      "epoch": 0.9844559585492227,
+      "grad_norm": 0.4485471844673157,
+      "learning_rate": 0.00013575129533678756,
+      "loss": 0.3755,
+      "step": 190
+    },
+    {
+      "epoch": 1.0362694300518134,
+      "grad_norm": 0.39652231335639954,
+      "learning_rate": 0.0001322970639032815,
+      "loss": 0.2445,
+      "step": 200
+    },
+    {
+      "epoch": 1.0880829015544042,
+      "grad_norm": 0.36412283778190613,
+      "learning_rate": 0.00012884283246977548,
+      "loss": 0.2351,
+      "step": 210
+    },
+    {
+      "epoch": 1.1398963730569949,
+      "grad_norm": 0.21277184784412384,
+      "learning_rate": 0.00012538860103626943,
+      "loss": 0.1115,
+      "step": 220
+    },
+    {
+      "epoch": 1.1917098445595855,
+      "grad_norm": 0.4270087480545044,
+      "learning_rate": 0.00012193436960276338,
+      "loss": 0.1656,
+      "step": 230
+    },
+    {
+      "epoch": 1.2435233160621761,
+      "grad_norm": 0.35429275035858154,
+      "learning_rate": 0.00011848013816925734,
+      "loss": 0.2019,
+      "step": 240
+    },
+    {
+      "epoch": 1.2953367875647668,
+      "grad_norm": 0.5731873512268066,
+      "learning_rate": 0.0001150259067357513,
+      "loss": 0.193,
+      "step": 250
+    },
+    {
+      "epoch": 1.3471502590673574,
+      "grad_norm": 0.18436703085899353,
+      "learning_rate": 0.00011157167530224525,
+      "loss": 0.2204,
+      "step": 260
+    },
+    {
+      "epoch": 1.3989637305699483,
+      "grad_norm": 0.6231918334960938,
+      "learning_rate": 0.0001081174438687392,
+      "loss": 0.2204,
+      "step": 270
+    },
+    {
+      "epoch": 1.450777202072539,
+      "grad_norm": 0.27956509590148926,
+      "learning_rate": 0.00010466321243523317,
+      "loss": 0.1864,
+      "step": 280
+    },
+    {
+      "epoch": 1.5025906735751295,
+      "grad_norm": 0.24223612248897552,
+      "learning_rate": 0.00010120898100172711,
+      "loss": 0.1985,
+      "step": 290
+    },
+    {
+      "epoch": 1.5544041450777202,
+      "grad_norm": 0.28999006748199463,
+      "learning_rate": 9.775474956822108e-05,
+      "loss": 0.1322,
+      "step": 300
+    },
+    {
+      "epoch": 1.6062176165803108,
+      "grad_norm": 0.505622923374176,
+      "learning_rate": 9.430051813471503e-05,
+      "loss": 0.1745,
+      "step": 310
+    },
+    {
+      "epoch": 1.6580310880829017,
+      "grad_norm": 0.17805594205856323,
+      "learning_rate": 9.084628670120899e-05,
+      "loss": 0.229,
+      "step": 320
+    },
+    {
+      "epoch": 1.709844559585492,
+      "grad_norm": 0.8911346197128296,
+      "learning_rate": 8.739205526770295e-05,
+      "loss": 0.2056,
+      "step": 330
+    },
+    {
+      "epoch": 1.761658031088083,
+      "grad_norm": 0.2521348297595978,
+      "learning_rate": 8.39378238341969e-05,
+      "loss": 0.2274,
+      "step": 340
+    },
+    {
+      "epoch": 1.8134715025906736,
+      "grad_norm": 0.1958165019750595,
+      "learning_rate": 8.048359240069086e-05,
+      "loss": 0.1346,
+      "step": 350
+    },
+    {
+      "epoch": 1.8652849740932642,
+      "grad_norm": 0.43222665786743164,
+      "learning_rate": 7.702936096718481e-05,
+      "loss": 0.1926,
+      "step": 360
+    },
+    {
+      "epoch": 1.917098445595855,
+      "grad_norm": 0.28354278206825256,
+      "learning_rate": 7.357512953367876e-05,
+      "loss": 0.1491,
+      "step": 370
+    },
+    {
+      "epoch": 1.9689119170984455,
+      "grad_norm": 0.30970773100852966,
+      "learning_rate": 7.012089810017272e-05,
+      "loss": 0.1939,
+      "step": 380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 579,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6349087813140480.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

capybara-finetuned/checkpoint-386/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
+size 5304

capybara-finetuned/checkpoint-579/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Nous-Capybara-3B-V1.9
+library_name: peft
+---
+
+# 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 0.14.0

capybara-finetuned/checkpoint-579/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Capybara-3B-V1.9",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

capybara-finetuned/checkpoint-579/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3e58810019f8c2423473124d01849395572ed748ab106aff696e68fe511594
+size 41977424

capybara-finetuned/checkpoint-579/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae81316b6c06fe5011bed6387e38d2e9e6d59b269947e0e98a135f250e53431
+size 84100858

capybara-finetuned/checkpoint-579/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be5bd0f0585baf47114de4868010f1d69cccda30c0451f6ffa7a6656210a61c
+size 14244

capybara-finetuned/checkpoint-579/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70d513d90f98dc0b17bacf317603627627da3ea2748eb84b7ab7f4d8ec7a878
+size 988

capybara-finetuned/checkpoint-579/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180e243f8de76fb954da6fdb3fad5a9f4cc7a2aa5ac46cf1ccaa53c9bb3946ef
+size 1064

capybara-finetuned/checkpoint-579/trainer_state.json

@@ -0,0 +1,433 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 579,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05181347150259067,
+      "grad_norm": 0.8095124363899231,
+      "learning_rate": 0.00019792746113989637,
+      "loss": 12.3719,
+      "step": 10
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.2720714509487152,
+      "learning_rate": 0.00019447322970639035,
+      "loss": 0.2877,
+      "step": 20
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 0.3335513770580292,
+      "learning_rate": 0.0001910189982728843,
+      "loss": 0.3723,
+      "step": 30
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.21196776628494263,
+      "learning_rate": 0.00018756476683937825,
+      "loss": 0.1598,
+      "step": 40
+    },
+    {
+      "epoch": 0.25906735751295334,
+      "grad_norm": 0.41250184178352356,
+      "learning_rate": 0.0001841105354058722,
+      "loss": 0.1899,
+      "step": 50
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.2743557095527649,
+      "learning_rate": 0.00018065630397236614,
+      "loss": 0.3541,
+      "step": 60
+    },
+    {
+      "epoch": 0.3626943005181347,
+      "grad_norm": 0.28188714385032654,
+      "learning_rate": 0.00017720207253886012,
+      "loss": 0.1689,
+      "step": 70
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.3063858151435852,
+      "learning_rate": 0.00017374784110535407,
+      "loss": 0.2957,
+      "step": 80
+    },
+    {
+      "epoch": 0.46632124352331605,
+      "grad_norm": 0.24155083298683167,
+      "learning_rate": 0.00017029360967184802,
+      "loss": 0.2411,
+      "step": 90
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.3580751121044159,
+      "learning_rate": 0.00016683937823834197,
+      "loss": 0.2035,
+      "step": 100
+    },
+    {
+      "epoch": 0.5699481865284974,
+      "grad_norm": 0.32368239760398865,
+      "learning_rate": 0.00016338514680483594,
+      "loss": 0.2863,
+      "step": 110
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 0.31771329045295715,
+      "learning_rate": 0.0001599309153713299,
+      "loss": 0.2815,
+      "step": 120
+    },
+    {
+      "epoch": 0.6735751295336787,
+      "grad_norm": 0.1532900333404541,
+      "learning_rate": 0.00015647668393782384,
+      "loss": 0.1949,
+      "step": 130
+    },
+    {
+      "epoch": 0.7253886010362695,
+      "grad_norm": 0.41243669390678406,
+      "learning_rate": 0.0001530224525043178,
+      "loss": 0.1595,
+      "step": 140
+    },
+    {
+      "epoch": 0.7772020725388601,
+      "grad_norm": 0.10424460470676422,
+      "learning_rate": 0.00014956822107081174,
+      "loss": 0.1694,
+      "step": 150
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 0.2025623470544815,
+      "learning_rate": 0.0001461139896373057,
+      "loss": 0.2369,
+      "step": 160
+    },
+    {
+      "epoch": 0.8808290155440415,
+      "grad_norm": 0.1760733723640442,
+      "learning_rate": 0.00014265975820379966,
+      "loss": 0.3239,
+      "step": 170
+    },
+    {
+      "epoch": 0.9326424870466321,
+      "grad_norm": 0.10223771631717682,
+      "learning_rate": 0.0001392055267702936,
+      "loss": 0.1242,
+      "step": 180
+    },
+    {
+      "epoch": 0.9844559585492227,
+      "grad_norm": 0.4485471844673157,
+      "learning_rate": 0.00013575129533678756,
+      "loss": 0.3755,
+      "step": 190
+    },
+    {
+      "epoch": 1.0362694300518134,
+      "grad_norm": 0.39652231335639954,
+      "learning_rate": 0.0001322970639032815,
+      "loss": 0.2445,
+      "step": 200
+    },
+    {
+      "epoch": 1.0880829015544042,
+      "grad_norm": 0.36412283778190613,
+      "learning_rate": 0.00012884283246977548,
+      "loss": 0.2351,
+      "step": 210
+    },
+    {
+      "epoch": 1.1398963730569949,
+      "grad_norm": 0.21277184784412384,
+      "learning_rate": 0.00012538860103626943,
+      "loss": 0.1115,
+      "step": 220
+    },
+    {
+      "epoch": 1.1917098445595855,
+      "grad_norm": 0.4270087480545044,
+      "learning_rate": 0.00012193436960276338,
+      "loss": 0.1656,
+      "step": 230
+    },
+    {
+      "epoch": 1.2435233160621761,
+      "grad_norm": 0.35429275035858154,
+      "learning_rate": 0.00011848013816925734,
+      "loss": 0.2019,
+      "step": 240
+    },
+    {
+      "epoch": 1.2953367875647668,
+      "grad_norm": 0.5731873512268066,
+      "learning_rate": 0.0001150259067357513,
+      "loss": 0.193,
+      "step": 250
+    },
+    {
+      "epoch": 1.3471502590673574,
+      "grad_norm": 0.18436703085899353,
+      "learning_rate": 0.00011157167530224525,
+      "loss": 0.2204,
+      "step": 260
+    },
+    {
+      "epoch": 1.3989637305699483,
+      "grad_norm": 0.6231918334960938,
+      "learning_rate": 0.0001081174438687392,
+      "loss": 0.2204,
+      "step": 270
+    },
+    {
+      "epoch": 1.450777202072539,
+      "grad_norm": 0.27956509590148926,
+      "learning_rate": 0.00010466321243523317,
+      "loss": 0.1864,
+      "step": 280
+    },
+    {
+      "epoch": 1.5025906735751295,
+      "grad_norm": 0.24223612248897552,
+      "learning_rate": 0.00010120898100172711,
+      "loss": 0.1985,
+      "step": 290
+    },
+    {
+      "epoch": 1.5544041450777202,
+      "grad_norm": 0.28999006748199463,
+      "learning_rate": 9.775474956822108e-05,
+      "loss": 0.1322,
+      "step": 300
+    },
+    {
+      "epoch": 1.6062176165803108,
+      "grad_norm": 0.505622923374176,
+      "learning_rate": 9.430051813471503e-05,
+      "loss": 0.1745,
+      "step": 310
+    },
+    {
+      "epoch": 1.6580310880829017,
+      "grad_norm": 0.17805594205856323,
+      "learning_rate": 9.084628670120899e-05,
+      "loss": 0.229,
+      "step": 320
+    },
+    {
+      "epoch": 1.709844559585492,
+      "grad_norm": 0.8911346197128296,
+      "learning_rate": 8.739205526770295e-05,
+      "loss": 0.2056,
+      "step": 330
+    },
+    {
+      "epoch": 1.761658031088083,
+      "grad_norm": 0.2521348297595978,
+      "learning_rate": 8.39378238341969e-05,
+      "loss": 0.2274,
+      "step": 340
+    },
+    {
+      "epoch": 1.8134715025906736,
+      "grad_norm": 0.1958165019750595,
+      "learning_rate": 8.048359240069086e-05,
+      "loss": 0.1346,
+      "step": 350
+    },
+    {
+      "epoch": 1.8652849740932642,
+      "grad_norm": 0.43222665786743164,
+      "learning_rate": 7.702936096718481e-05,
+      "loss": 0.1926,
+      "step": 360
+    },
+    {
+      "epoch": 1.917098445595855,
+      "grad_norm": 0.28354278206825256,
+      "learning_rate": 7.357512953367876e-05,
+      "loss": 0.1491,
+      "step": 370
+    },
+    {
+      "epoch": 1.9689119170984455,
+      "grad_norm": 0.30970773100852966,
+      "learning_rate": 7.012089810017272e-05,
+      "loss": 0.1939,
+      "step": 380
+    },
+    {
+      "epoch": 2.0207253886010363,
+      "grad_norm": 0.23131532967090607,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.1619,
+      "step": 390
+    },
+    {
+      "epoch": 2.0725388601036268,
+      "grad_norm": 0.6155455708503723,
+      "learning_rate": 6.321243523316063e-05,
+      "loss": 0.1383,
+      "step": 400
+    },
+    {
+      "epoch": 2.1243523316062176,
+      "grad_norm": 0.4131735563278198,
+      "learning_rate": 5.9758203799654574e-05,
+      "loss": 0.1434,
+      "step": 410
+    },
+    {
+      "epoch": 2.1761658031088085,
+      "grad_norm": 0.3871082365512848,
+      "learning_rate": 5.6303972366148536e-05,
+      "loss": 0.0827,
+      "step": 420
+    },
+    {
+      "epoch": 2.227979274611399,
+      "grad_norm": 0.8619069457054138,
+      "learning_rate": 5.284974093264249e-05,
+      "loss": 0.161,
+      "step": 430
+    },
+    {
+      "epoch": 2.2797927461139897,
+      "grad_norm": 0.3584190905094147,
+      "learning_rate": 4.939550949913645e-05,
+      "loss": 0.1341,
+      "step": 440
+    },
+    {
+      "epoch": 2.33160621761658,
+      "grad_norm": 0.2826884090900421,
+      "learning_rate": 4.59412780656304e-05,
+      "loss": 0.1257,
+      "step": 450
+    },
+    {
+      "epoch": 2.383419689119171,
+      "grad_norm": 0.4198673367500305,
+      "learning_rate": 4.248704663212436e-05,
+      "loss": 0.1216,
+      "step": 460
+    },
+    {
+      "epoch": 2.4352331606217614,
+      "grad_norm": 0.582490086555481,
+      "learning_rate": 3.9032815198618314e-05,
+      "loss": 0.1325,
+      "step": 470
+    },
+    {
+      "epoch": 2.4870466321243523,
+      "grad_norm": 0.7895885109901428,
+      "learning_rate": 3.557858376511227e-05,
+      "loss": 0.128,
+      "step": 480
+    },
+    {
+      "epoch": 2.538860103626943,
+      "grad_norm": 0.24237169325351715,
+      "learning_rate": 3.212435233160622e-05,
+      "loss": 0.1391,
+      "step": 490
+    },
+    {
+      "epoch": 2.5906735751295336,
+      "grad_norm": 0.46788838505744934,
+      "learning_rate": 2.8670120898100174e-05,
+      "loss": 0.1712,
+      "step": 500
+    },
+    {
+      "epoch": 2.6424870466321244,
+      "grad_norm": 0.2091088891029358,
+      "learning_rate": 2.521588946459413e-05,
+      "loss": 0.1146,
+      "step": 510
+    },
+    {
+      "epoch": 2.694300518134715,
+      "grad_norm": 0.3197329342365265,
+      "learning_rate": 2.1761658031088085e-05,
+      "loss": 0.1483,
+      "step": 520
+    },
+    {
+      "epoch": 2.7461139896373057,
+      "grad_norm": 0.5090299844741821,
+      "learning_rate": 1.830742659758204e-05,
+      "loss": 0.1418,
+      "step": 530
+    },
+    {
+      "epoch": 2.7979274611398965,
+      "grad_norm": 0.1630585491657257,
+      "learning_rate": 1.4853195164075994e-05,
+      "loss": 0.1563,
+      "step": 540
+    },
+    {
+      "epoch": 2.849740932642487,
+      "grad_norm": 0.9052726626396179,
+      "learning_rate": 1.139896373056995e-05,
+      "loss": 0.1299,
+      "step": 550
+    },
+    {
+      "epoch": 2.901554404145078,
+      "grad_norm": 0.21230316162109375,
+      "learning_rate": 7.944732297063904e-06,
+      "loss": 0.1496,
+      "step": 560
+    },
+    {
+      "epoch": 2.9533678756476682,
+      "grad_norm": 0.4288373291492462,
+      "learning_rate": 4.490500863557859e-06,
+      "loss": 0.1735,
+      "step": 570
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 579,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9523631719710720.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

capybara-finetuned/checkpoint-579/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
+size 5304

capybara-finetuned/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

capybara-finetuned/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50279": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

capybara-finetuned/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
+size 5304

requirements.txt

@@ -0,0 +1,7 @@
+transformers==4.37.2
+accelerate==0.27.2
+torch>=2.1.0
+peft==0.8.2
+bitsandbytes==0.43.1
+uvicorn
+fastapi