Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,127 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
+tags:
+- generated_from_trainer
+datasets:
+- instruction_solution_to_thought_dataset.jsonl
+model-index:
+- name: outputs_solution_to_thought
+  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: `0.7.0`
+```yaml
+# Base model configuration
+base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
+load_in_4bit: true
+
+# Dataset configuration
+datasets:
+  - path: instruction_solution_to_thought_dataset.jsonl
+    type: chat_template
+
+# Chat template
+chat_template: chatml
+
+# LoRA adapter configuration
+adapter: lora
+lora_r: 16
+lora_alpha: 16
+lora_dropout: 0
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+  - gate_proj
+  - up_proj
+  - down_proj
+
+# Training hyperparameters
+max_seq_length: 128000
+micro_batch_size: 2
+gradient_accumulation_steps: 8
+learning_rate: 3e-5
+num_epochs: 2
+warmup_steps: 100
+optimizer: adamw_8bit
+weight_decay: 0.01
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+output_dir: ./outputs_solution_to_thought
+seed: 3407
+merge_lora: true
+hf_upload: true
+hf_repo: secemp9/TraceBack-12b
+xformers_attention:
+flash_attention: True
+#lora_mlp_kernel: true
+#lora_qkv_kernel: true
+#lora_o_kernel: true
+#fp16: true
+#load_in_8bit: true  # Enable 8-bit loading for LoRA finetuning
+bf16: true          # Enable BF16 mixed precision
+# Multi-GPU training with DeepSpeed
+deepspeed: deepspeed_configs/zero2.json
+
+# Optional: Enable gradient checkpointing
+gradient_checkpointing: true
+
+```
+
+</details><br>
+
+# outputs_solution_to_thought
+
+This model is a fine-tuned version of [unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit) on the instruction_solution_to_thought_dataset.jsonl 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: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 3407
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,50 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "unsloth_fixed": true,
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 131072,
+  "pad_token_id": 10,
+  "transformers_version": "4.48.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef793aab7f7093b35bc89285e1e118ed8caaf3d549a884b4080115609d36044
+size 4999749144

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d0a9815ee07ce4289084930adc2d22c31dfa33af59c4bc3140632625b9813a
+size 3311649399

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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292