Upload folder using huggingface_hub

README.md

@@ -0,0 +1,142 @@
+---
+license: other
+base_model: IndexTeam/Index-1.9B-Chat
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: IndexTeam/Index-1.9B-Chat
+model_type: IndexForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: gardner/glaive-function-calling-v2-sharegpt
+    type: sharegpt
+    conversation: index_chat
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+output_dir: ./outputs/out
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+trust_remote_code: true
+
+wandb_project: index-1.9b
+wandb_entity:
+wandb_watch:
+wandb_name: index-1.9b
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 4
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 5e-6
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 2
+eval_table_size:
+saves_per_epoch: 2
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: </s>
+
+```
+
+</details><br>
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/intervitens/index-1.9b/runs/a7r2nnwc)
+# outputs/out
+
+This model is a fine-tuned version of [IndexTeam/Index-1.9B-Chat](https://huggingface.co/IndexTeam/Index-1.9B-Chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4745
+
+## 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: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 5.3244        | 0.0021 | 1    | 5.2299          |
+| 0.6569        | 0.4992 | 237  | 0.6106          |
+| 0.5053        | 0.9984 | 474  | 0.5233          |
+| 0.472         | 1.4779 | 711  | 0.5007          |
+| 0.4849        | 1.9771 | 948  | 0.4863          |
+| 0.4611        | 2.4576 | 1185 | 0.4794          |
+| 0.3926        | 2.9568 | 1422 | 0.4756          |
+| 0.4171        | 3.4368 | 1659 | 0.4747          |
+| 0.4246        | 3.9360 | 1896 | 0.4745          |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "IndexTeam/Index-1.9B-Chat",
+  "architectures": [
+    "IndexForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "IndexTeam/Index-1.9B-Chat--configuration_index.IndexConfig",
+    "AutoModelForCausalLM": "IndexTeam/Index-1.9B-Chat--modeling_index.IndexForCausalLM",
+    "AutoModelForSequenceClassification": "IndexTeam/Index-1.9B-Chat--modeling_index.IndexForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.01,
+  "intermediate_size": 5888,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "model_type": "index",
+  "norm_head": 1,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 65029
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "repetition_penalty": 1.1,
+  "temperature": 0.3,
+  "top_k": 5,
+  "top_p": 0.8,
+  "transformers_version": "4.42.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a844a55901a4cacb355b2d53e5465e2814fdec0ad48d516840a6a8c74885d8
+size 4612043068

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 sha256:3a11626b3c80cbfdd5f4b5585fce8938d178f3a0df739c3dd1c708ce944878af
+size 1010047

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": 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
+    },
+    "3": {
+      "content": "reserved_0",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "reserved_1",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "IndexTeam/Index-1.9B-Chat--tokenization_index.IndexTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ unk_token + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'reserved_0' + content.strip() + 'reserved_1' }}{% elif message['role'] == 'assistant' %}{{ content.strip() }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "decode_with_prefix_space": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1e+30,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "IndexTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}