Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,190 @@
+---
+license: mit
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+<!-- 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: `0.4.0`
+
+```yaml
+base_model: mistralai/Mistral-7B-v0.1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizergin
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  # This will be the path used for the data when it is saved to the Volume in the cloud.
+  - path: data.jsonl
+    ds_type: json
+    type:
+      # JSONL file contains question, context, answer fields per line.
+      # This gets mapped to instruction, input, output axolotl tags.
+      field_instruction: instruction
+      field_input: input
+      field_output: output
+      # Format is used by axolotl to generate the prompt.
+      format: |-
+        [INST]{input}
+        {instruction} [/INST] 
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./lora-out
+
+sequence_len: 4096
+sample_packing: false
+eval_sample_packing: false
+pad_to_sequence_len: false
+
+adapter: lora
+lora_model_dir:
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 32
+num_epochs: 4
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 0.0001
+
+bf16: auto
+fp16: false
+tf32: false
+train_on_inputs: false
+group_by_length: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+save_steps:
+debug:
+deepspeed: /root/axolotl/deepspeed_configs/zero3_bf16.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+
+```
+
+</details><br>
+
+# Mistral Sentiment Analysis
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [FinGPT Sentiment](https://huggingface.co/datasets/FinGPT/fingpt-sentiment-train) dataset. It is intended to be used for sentiment analysis tasks for financial data. See the [FinGPT Project](https://github.com/AI4Finance-Foundation/FinGPT) for more information.
+It achieves the following results on the evaluation set:
+* Loss: 0.1598
+
+## Ollama Example
+
+```bash
+ollama run chand1012/mistral_sentiment
+>>> Apple (NASDAQ:AAPL) Up Fractionally despite Rising Vision Pro Returns Please choose an answer from {negative/neutral/positive} 
+ positive
+```
+
+## Python Example
+
+```python
+from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM, LlamaTokenizerFast
+from peft import PeftModel  # 0.8.2
+
+# Load Models
+base_model = "mistralai/Mistral-7B-v0.1" 
+peft_model = "TimeSurgeLabs/mistral_sentiment_lora"
+tokenizer = LlamaTokenizerFast.from_pretrained(base_model, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+model = LlamaForCausalLM.from_pretrained(base_model, trust_remote_code=True, device_map = "cuda:0", load_in_8bit = True,)
+model = PeftModel.from_pretrained(model, peft_model)
+model = model.eval()
+
+# Make prompts
+prompt = [
+'''Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}
+Input: FINANCING OF ASPOCOMP 'S GROWTH Aspocomp is aggressively pursuing its growth strategy by increasingly focusing on technologically more demanding HDI printed circuit boards PCBs .
+Answer: ''',
+'''Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}
+Input: According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .
+Answer: ''',
+'''Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}
+Input: A tinyurl link takes users to a scamming site promising that users can earn thousands of dollars by becoming a Google ( NASDAQ : GOOG ) Cash advertiser .
+Answer: ''',
+]
+
+# Generate results
+tokens = tokenizer(prompt, return_tensors='pt', padding=True, max_length=512)
+res = model.generate(**tokens, max_length=512)
+res_sentences = [tokenizer.decode(i) for i in res]
+out_text = [o.split("Answer: ")[1] for o in res_sentences]
+
+# show results
+for sentiment in out_text:
+    print(sentiment)
+
+# Output:    
+# positive
+# neutral
+# negative
+```
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+* learning_rate: 0.0001
+* train_batch_size: 32
+* eval_batch_size: 32
+* seed: 42
+* distributed_type: multi-GPU
+* num_devices: 2
+* total_train_batch_size: 64
+* total_eval_batch_size: 64
+* optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
+* lr_scheduler_type: cosine
+* lr_scheduler_warmup_steps: 10
+* num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0678        | 1.0   | 1140 | 0.1124          |
+| 0.1339        | 2.0   | 2280 | 0.1008          |
+| 0.0497        | 3.0   | 3420 | 0.1146          |
+| 0.0016        | 4.0   | 4560 | 0.1598          |
+
+### Framework versions
+
+* PEFT 0.8.2
+* Transformers 4.38.0.dev0
+* Pytorch 2.1.2+cu121
+* Datasets 2.17.0
+* Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "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": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fee993242168c43115a0b719d530b6355a11e3756b044504c4c837f1ff9f44a
+size 83946192

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

ggml-adapter-model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5460b3f6415dd6264e7b288ea5251e6451abcfe9f57011a1e96dd4ba992ab28a
+size 167800832

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "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
+}