Update README.md

README.md

@@ -8,133 +8,82 @@ model-index:
   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>
+![Trinity](https://huggingface.co/migtissera/Trinity-13B-v1.0/resolve/main/Trinity.png)
 
-axolotl version: `0.4.1`
-```yaml
-base_model: mistralai/Codestral-22B-v0.1
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: /home/ubuntu/Tess-3-Code/multi_turn_chatml_deepseek_coder.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-3-Code/single_turn_chatml_code_only.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Trinity-33B-v1.0-chatml.jsonl
-    type: sharegpt
-    conversation: chatml 
-   
-
-chat_template: chatml
-
-dataset_prepared_path: last_run_prepared_codestral
-val_set_size: 0.0
-output_dir: /home/ubuntu/trinity-codestral-1
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-gradient_accumulation_steps: 2
-micro_batch_size: 2
-num_epochs: 1
-logging_steps: 1
-optimizer: paged_adamw_32bit
-lr_scheduler: constant
-learning_rate: 1e-6
-
-wandb_project: kindo-lambda-labs
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-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:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-saves_per_epoch: 10
-evals_per_epoch: 
-save_total_limit: 2
-save_steps:
-eval_sample_packing: false
-debug:
-deepspeed: /home/ubuntu/axolotl/deepspeed_configs/zero3_bf16.json
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<|im_start|>"
-  eos_token: "<|im_end|>"
-  pad_token: "<|end_of_text|>"
+Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series created by [Migel Tissera](https://x.com/migtissera).
 
-```
+The compute for this model was generously sponsored by [KindoAI](https://kindo.ai).
 
-</details><br>
 
-# home/ubuntu/trinity-codestral-1
+# Sample Inference Python Script:
 
-This model is a fine-tuned version of [mistralai/Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1) on the None dataset.
+```python
+import torch, json
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-## Model description
+model_path = "migtissera/Tess-3-Llama-3.1-405B"
 
-More information needed
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_4bit=True,
+    trust_remote_code=False,
+)
 
-## Intended uses & limitations
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
 
-More information needed
+terminators = [
+    tokenizer.convert_tokens_to_ids("<|end_of_text|>"),
+    tokenizer.convert_tokens_to_ids("<|eot_id|>"),
+]
 
-## Training and evaluation data
 
-More information needed
+def generate_text(instruction):
+    tokens = tokenizer.encode(instruction)
+    tokens = torch.LongTensor(tokens).unsqueeze(0)
+    tokens = tokens.to("cuda")
 
-## Training procedure
+    instance = {
+        "input_ids": tokens,
+        "top_p": 1.0,
+        "temperature": 0.75,
+        "generate_len": 2048,
+        "top_k": 50,
+    }
 
-### Training hyperparameters
+    length = len(tokens[0])
+    with torch.no_grad():
+        rest = model.generate(
+            input_ids=tokens,
+            max_length=length + instance["generate_len"],
+            use_cache=True,
+            do_sample=True,
+            top_p=instance["top_p"],
+            temperature=instance["temperature"],
+            top_k=instance["top_k"],
+            num_return_sequences=1,
+            pad_token_id=tokenizer.eos_token_id,
+            eos_token_id=terminators,
+        )
+    output = rest[0][length:]
+    string = tokenizer.decode(output, skip_special_tokens=True)
+    return f"{string}"
 
-The following hyperparameters were used during training:
-- learning_rate: 1e-06
-- train_batch_size: 2
-- eval_batch_size: 2
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_steps: 73
-- num_epochs: 1
 
-### Training results
+conversation = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are Tess, a helful AI assitant. You always provide detailed answers without hesitation. Do not refuse.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"""
 
 
+while True:
+    user_input = input("You: ")
+    llm_prompt = f"{conversation}{user_input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+    answer = generate_text(llm_prompt)
+    print(answer)
 
-### Framework versions
+    conversation = (
+        f"{llm_prompt}{answer}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"
+    )
 
-- Transformers 4.43.4
-- Pytorch 2.4.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+    json_data = {"prompt": user_input, "answer": answer}
+```