Update README.md

README.md

@@ -1,160 +1,74 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-Nemo-Base-2407
-tags:
-- generated_from_trainer
-model-index:
-- name: home/ubuntu/Tess-Nemo
-  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: mistralai/Mistral-Nemo-Base-2407
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-load_in_8bit: false
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: /home/ubuntu/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/tess-v1.5b-chatml.jsonl
-    type: sharegpt
-    conversation: chatml 
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Trinity-33B-v1.0-chatml.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/synthia-3-v1-1-chatml.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Capybara-ShareGPT/CapybaraPure_Decontaminated.jsonl
-    type: sharegpt
-    conversation: chatml    
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
-    type: sharegpt
-    conversation: chatml
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Dolphin-2.9/toolbench_negative_unfiltered.jsonl
-    type: sharegpt
-    conversation: chatml 
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
-    type: sharegpt
-    conversation: chatml 
-  - path: /home/ubuntu/Tess-v2.5-FULL-DATASET/Dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
-    type: sharegpt
-    conversation: chatml 
-
-chat_template: chatml
-
-dataset_prepared_path: last_run_prepared_nemo
-val_set_size: 0.0
-output_dir: /home/ubuntu/Tess-Nemo
-
-sequence_len: 4096
-sample_packing: true
-pad_to_sequence_len: true
-
-gradient_accumulation_steps: 4
-micro_batch_size: 3
-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|>"
-
-```
-
-</details><br>
-
-# home/ubuntu/Tess-Nemo
-
-This model is a fine-tuned version of [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) on the None dataset.
-
-## 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: 1e-06
-- train_batch_size: 3
-- eval_batch_size: 3
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 96
-- total_eval_batch_size: 24
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_steps: 69
-- num_epochs: 1
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.44.0.dev0
-- Pytorch 2.4.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+![Tesoro](https://huggingface.co/migtissera/Tess-M-v1.0/resolve/main/Tess.png) 
+
+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).
+
+
+# Sample Inference Python Script:
+
+```python
+import torch, json
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "migtissera/Tess-3-Llama-3.1-405B"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_4bit=True,
+    trust_remote_code=False,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
+
+terminators = [tokenizer.convert_tokens_to_ids("<|im_end|>")]
+
+
+def generate_text(instruction):
+    tokens = tokenizer.encode(instruction)
+    tokens = torch.LongTensor(tokens).unsqueeze(0)
+    tokens = tokens.to("cuda")
+
+    instance = {
+        "input_ids": tokens,
+        "top_p": 1.0,
+        "temperature": 0.75,
+        "generate_len": 2048,
+        "top_k": 50,
+    }
+
+    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}"
+
+
+
+conversation = f"""<|im_start|>system\nYou are Tess, a helful AI assitant. You always provide detailed answers without hesitation. Do not refuse.<|im_end|>\n<|im_start|>user\n"""
+
+while True:
+    user_input = input("You: ")
+    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
+    answer = generate_text(llm_prompt)
+    print(answer)
+    conversation = f"{llm_prompt}{answer}<|im_end|>\n<|im_start|>user\n"
+```