Upload folder using huggingface_hub

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+dtype: bfloat16
+tags:
+- merge
+---
+
+
+# Results:
+T: 🟦
+Model: CultriX/MistralTrix-v1 📑
+Average: 73.39
+ARC: 72.27
+HellaSwag: 88.33
+MMLU: 65.24
+TruthfulQA: 70.73
+Winogrande: 80.98
+GSM8K: 62.77
+
+# Edit/Disclaimer:
+Currently the #1 ranked 7B LLM on the LLM Leaderboards, woah!
+I did not expect that result at all and am in no way a professional when it comes to LLM's or computer science in general,
+just a guy that likes to nerd about and tinker around. 
+
+For those wondering how I achieved this, the answer is that I simply attempted to apply the techniques outlined in this amazing article myself: https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac
+Therefore, all credit basically goes to the guy who wrote that. 
+He offers the exact Colab notebook I used to train this model for free, as well as a really nice GitHub page I hope he doesn't mind me sharing: https://github.com/mlabonne/llm-course/
+So huge thank you to him for sharing his knowledge and learning me a thing or two in the process!
+
+# GGUF
+I attempted to quantisize the model myself, which again I pretty much have no clue about, but it seems to run fine for me when I test them:
+https://huggingface.co/CultriX/MistralTrix-v1-GGUF
+
+I'll say it one more time though:
+"I am a complete beginner to all of this, so if these do end up sucking don't be surprised."
+
+You have been warned :)
+
+# Description:
+(trained on a single Colab GPU in less than a few hours)
+
+MistralTrix-v1 is an zyh3826/GML-Mistral-merged-v1 model that has been further fine-tuned with Direct Preference Optimization (DPO) using Intel's dataset for neural-chat-7b-v3-1.
+It surpasses the original model on several benchmarks (see results).
+
+It is directly inspired by the RLHF process described by Intel/neural-chat-7b-v3-1's authors to improve performance. 
+I used the same dataset and reformatted it to apply the ChatML template.
+
+The code to train this model is available on Google Colab and GitHub. 
+Fine-tuning took about an hour on Google Colab A-1000 GPU with 40GB VRAM.
+
+# TRAINING SPECIFICATIONS
+> LoRA configuration
+peft_config = LoraConfig(
+    r=16,
+    lora_alpha=16,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
+)
+
+> Model to fine-tune
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    load_in_4bit=True
+)
+model.config.use_cache = False
+
+> Reference model
+ref_model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    load_in_4bit=True
+)
+
+> Training arguments
+training_args = TrainingArguments(
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    gradient_checkpointing=True,
+    learning_rate=5e-5,
+    lr_scheduler_type="cosine",
+    max_steps=200,
+    save_strategy="no",
+    logging_steps=1,
+    output_dir=new_model,
+    optim="paged_adamw_32bit",
+    warmup_steps=100,
+    bf16=True,
+    report_to="wandb",
+)
+
+> Create DPO trainer
+dpo_trainer = DPOTrainer(
+    model,
+    ref_model,
+    args=training_args,
+    train_dataset=dataset,
+    tokenizer=tokenizer,
+    peft_config=peft_config,
+    beta=0.1,
+    max_prompt_length=1024,
+    max_length=1536,
+)

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/opt/llm/_models/MistralTrix-v1",
+  "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": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85527d78352d4bef2bdb86c636ec53ee8db344be45f359e28ec94fc23bef4729
+size 5067253800

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "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 +1,46 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}