Upload 9 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ggml-model-f16.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1 @@
+FROM ./ggml-model-f16.gguf

README.md

@@ -0,0 +1,169 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+tags:
+- generated_from_trainer
+model-index:
+- name: tinyllama-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.3.0`
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+is_llama_derived_model: true
+
+
+eval_sample_packing: False #Poco dato
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: data.json # or json
+    ds_type: json # see other options below
+    type: completion
+
+dataset_prepared_path:
+val_set_size: 0.05
+# output_dir: ./lora-out
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+
+# adapter: lora
+# lora_model_dir:
+# lora_r: 32
+# lora_alpha: 16
+# lora_dropout: 0.05
+# lora_target_linear: true
+# lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./tinyllama-out
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 8 #2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false #TODO: change to true
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+save_strategy: "no"
+
+warmup_steps: 10
+evals_per_epoch: 4
+# saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# tinyllama-out
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8806
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9894        | 0.13  | 1    | 1.5790          |
+| 1.915         | 0.26  | 2    | 1.4849          |
+| 1.642         | 0.52  | 4    | 1.4032          |
+| 1.5396        | 0.77  | 6    | 1.4059          |
+| 1.3746        | 1.03  | 8    | 1.4101          |
+| 0.9355        | 1.23  | 10   | 1.5147          |
+| 0.9266        | 1.48  | 12   | 1.5291          |
+| 0.8006        | 1.74  | 14   | 1.4724          |
+| 0.7664        | 2.0   | 16   | 1.4965          |
+| 0.4813        | 2.16  | 18   | 1.5715          |
+| 0.4193        | 2.42  | 20   | 1.5436          |
+| 0.364         | 2.68  | 22   | 1.6040          |
+| 0.3592        | 2.94  | 24   | 1.5823          |
+| 0.1884        | 3.13  | 26   | 1.6850          |
+| 0.159         | 3.39  | 28   | 1.8316          |
+| 0.1641        | 3.65  | 30   | 1.7286          |
+| 0.1512        | 3.9   | 32   | 1.7029          |
+| 0.1563        | 4.06  | 34   | 1.7033          |
+| 0.0696        | 4.32  | 36   | 1.7482          |
+| 0.0643        | 4.58  | 38   | 1.8069          |
+| 0.0662        | 4.84  | 40   | 1.8410          |
+| 0.0709        | 5.1   | 42   | 1.8529          |
+| 0.0344        | 5.26  | 44   | 1.8626          |
+| 0.0468        | 5.52  | 46   | 1.8716          |
+| 0.0328        | 5.77  | 48   | 1.8761          |
+| 0.0353        | 6.03  | 50   | 1.8789          |
+| 0.0375        | 6.23  | 52   | 1.8803          |
+| 0.0345        | 6.48  | 54   | 1.8802          |
+| 0.0346        | 6.74  | 56   | 1.8806          |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.0.1
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

ggml-model-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a729680294ea5f37ce4d9ceea6faf4b8d3a3c065083707d085b97d27cb2dc5
+size 2201017248

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c118c16a1a80d74217d3334fd295f2ca3a096b21ef81535bc804508a06403be
+size 2200164273

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}