Upload fine-tuned Llama 3.2 model with LoRA

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "base_model_name_or_path": "/Users/biomac/converted_llama_3_2_1b",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f457ec3ddb08fc06768867c876c674b2c39b730b457c6ea9c5572b249ba35ed
-size 4517152
+oid sha256:702ad3adb1b9901795aed92f924eedcfefeeb7a315e299dc4518d867ded60656
+size 5778752

checkpoint-233/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /Users/biomac/converted_llama_3_2_1b
+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 0.15.1

checkpoint-233/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/Users/biomac/converted_llama_3_2_1b",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-233/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702ad3adb1b9901795aed92f924eedcfefeeb7a315e299dc4518d867ded60656
+size 5778752

checkpoint-233/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42b7ba81ae40e367717b03c57540488948b889a969ca47606b33fc5f71524ce
+size 11606010

checkpoint-233/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2d8e50c2fc8e7f50ca5a741ea4cbc7854d053c3a464a90a36a47cdc38ebe96
+size 13990

checkpoint-233/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9fc23b13eff1be65c1dc3497088de0b3a3d9eee8e42c9dbfbb436015dab28b
+size 1064

checkpoint-233/trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9967914438502674,
+  "eval_steps": 500,
+  "global_step": 233,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0427807486631016,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 10.5827,
+      "step": 10
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001993540527265239,
+      "loss": 10.5932,
+      "step": 20
+    },
+    {
+      "epoch": 0.12834224598930483,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019674418752719833,
+      "loss": 10.6018,
+      "step": 30
+    },
+    {
+      "epoch": 0.1711229946524064,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019218264229806917,
+      "loss": 10.5882,
+      "step": 40
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018576143989814523,
+      "loss": 10.5865,
+      "step": 50
+    },
+    {
+      "epoch": 0.25668449197860965,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017761011919494488,
+      "loss": 10.5991,
+      "step": 60
+    },
+    {
+      "epoch": 0.2994652406417112,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016789312179720547,
+      "loss": 10.5906,
+      "step": 70
+    },
+    {
+      "epoch": 0.3422459893048128,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 10.5962,
+      "step": 80
+    },
+    {
+      "epoch": 0.3850267379679144,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014457383557765386,
+      "loss": 10.6006,
+      "step": 90
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001314419810670624,
+      "loss": 10.59,
+      "step": 100
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001176758281235155,
+      "loss": 10.5897,
+      "step": 110
+    },
+    {
+      "epoch": 0.5133689839572193,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010355308982181253,
+      "loss": 10.5836,
+      "step": 120
+    },
+    {
+      "epoch": 0.5561497326203209,
+      "grad_norm": Infinity,
+      "learning_rate": 8.935867285261978e-05,
+      "loss": 10.5922,
+      "step": 130
+    },
+    {
+      "epoch": 0.5989304812834224,
+      "grad_norm": Infinity,
+      "learning_rate": 7.537892992447273e-05,
+      "loss": 10.5835,
+      "step": 140
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": Infinity,
+      "learning_rate": 6.189588299436997e-05,
+      "loss": 10.6007,
+      "step": 150
+    },
+    {
+      "epoch": 0.6844919786096256,
+      "grad_norm": Infinity,
+      "learning_rate": 4.9181533865282706e-05,
+      "loss": 10.5927,
+      "step": 160
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": Infinity,
+      "learning_rate": 3.7492376926397964e-05,
+      "loss": 10.5852,
+      "step": 170
+    },
+    {
+      "epoch": 0.7700534759358288,
+      "grad_norm": Infinity,
+      "learning_rate": 2.7064224733963197e-05,
+      "loss": 10.5855,
+      "step": 180
+    },
+    {
+      "epoch": 0.8128342245989305,
+      "grad_norm": Infinity,
+      "learning_rate": 1.8107450819473503e-05,
+      "loss": 10.5925,
+      "step": 190
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0802745694960569e-05,
+      "loss": 10.5893,
+      "step": 200
+    },
+    {
+      "epoch": 0.8983957219251337,
+      "grad_norm": Infinity,
+      "learning_rate": 5.29747167209923e-06,
+      "loss": 10.5813,
+      "step": 210
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": Infinity,
+      "learning_rate": 1.7026900316098215e-06,
+      "loss": 10.6031,
+      "step": 220
+    },
+    {
+      "epoch": 0.983957219251337,
+      "grad_norm": Infinity,
+      "learning_rate": 9.092051569674631e-08,
+      "loss": 10.5864,
+      "step": 230
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 233,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 8838201401671680.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-233/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a917f57899e8c56d0800023a8f9e37ddddbb3fff7afcc0e427f9409cb6922b
+size 5368

special_tokens_map.json

@@ -2,28 +2,22 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -2,15 +2,15 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 1024
+      "Fixed": 256
     },
-    "direction": "Right",
+    "direction": "Left",
     "pad_to_multiple_of": null,
     "pad_id": 2,
     "pad_type_id": 0,
@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -41,7 +41,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],
@@ -276669,484 +276669,484 @@
         "ub"
       ],
       [
-        "▁",
-        "▁"
+        "▁▁",
+        "▁▁"
       ],
       [
         "▁▁",
-        "▁▁"
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁"
+        "▁▁",
+        "▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁",
-        "▁▁▁"
+        "▁▁",
+        "▁▁▁▁▁"
       ],
       [
         "▁▁",
         "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁"
+        "▁▁",
+        "▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁"
+        "▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
-        "▁"
+        "▁▁",
+        "▁▁▁"
       ],
       [
-        "▁",
+        "▁▁",
+        "▁▁▁▁▁▁▁▁▁"
+      ],
+      [
+        "▁▁",
         "▁▁▁▁▁▁▁"
       ],
       [
         "▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁",
+        "▁▁",
         "▁"
       ],
       [
-        "▁▁▁",
+        "▁▁▁▁",
         "▁▁"
       ],
       [
-        "▁",
+        "▁▁▁▁",
         "▁▁▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁",
+        "▁▁▁▁▁▁▁▁"
       ],
       [
         "▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
+        "▁▁▁▁",
         "▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁",
+        "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁"
+        "▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁",
+        "▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁",
+        "▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁"
+      ],
+      [
+        "▁▁▁▁▁▁▁▁",
         "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁"
+        "▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁",
+        "▁▁▁▁▁▁▁▁",
+        "▁"
+      ],
+      [
+        "▁▁▁▁▁",
         "▁▁"
       ],
       [
         "▁▁▁▁▁",
-        "▁"
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁",
+        "▁▁▁▁▁",
         "▁▁▁▁▁"
       ],
       [
-        "▁▁",
+        "▁▁▁▁▁",
+        "▁▁▁▁▁▁"
+      ],
+      [
+        "▁▁▁▁▁",
         "▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁"
       ],
       [
         "▁▁▁▁▁",
         "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁",
+        "▁"
+      ],
+      [
+        "▁▁▁▁▁▁",
         "▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁",
         "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁",
-        "▁"
+        "▁▁▁▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁",
-        "▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁",
+        "▁▁▁▁▁▁",
         "▁▁▁▁▁▁▁▁▁"
       ],
-      [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁"
-      ],
-      [
-        "▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁"
-      ],
       [
         "▁▁▁▁▁▁",
         "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁",
         "▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁",
         "▁▁"
       ],
       [
-        "▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁"
       ],
       [
-        "▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁",
+        "▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁"
+        "▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁",
         "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁",
         "▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁"
       ],
       [
-        "▁",
-        "▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁"
       ],
       [
-        "▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁���▁▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁"
       ],
       [
         "▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
+        "▁▁▁",
         "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁"
-      ],
-      [
-        "▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁",
+        "▁▁▁",
         "▁"
       ],
       [
-        "▁",
+        "▁▁▁▁▁▁▁▁▁",
         "▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁",
         "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁"
+        "▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁",
+        "▁"
       ],
       [
         "▁▁▁▁▁▁▁",
         "▁▁"
       ],
       [
-        "▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁",
-        "▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁",
+        "▁"
       ],
       [
-        "▁▁▁▁",
-        "▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁",
+        "▁▁▁▁▁▁▁▁▁▁▁",
         "▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+        "▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
+        "▁",
         "▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
+        "▁",
         "▁▁▁▁"
       ],
       [
         "▁",
-        "▁▁▁▁▁▁▁▁▁▁"
-      ],
-      [
-        "▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁"
-      ],
-      [
-        "▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁"
+        "▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "���▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
-        "▁"
+        "▁",
+        "▁▁▁"
       ],
       [
-        "▁▁▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁",
-        "▁▁▁▁▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
-        "▁▁▁▁▁▁▁▁▁▁▁",
-        "▁▁▁▁"
+        "▁",
+        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
       ],
       [
         "▁",
-        "▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+        "▁"
       ]
     ]
   }

tokenizer_config.json

@@ -6,7 +6,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -14,7 +14,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,21 +22,20 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
-  "legacy": false,
+  "legacy": true,
   "model_max_length": 2048,
   "pad_token": "</s>",
-  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",