Upload 10 files

README.md

@@ -1,3 +1,53 @@
----
-license: apache-2.0
----
+# Mistral + LoRA Fine-Tuning
+
+Lightweight fine-tuning setup for adapting a Mistral-architecture model using LoRA.  
+The project keeps everything modular: base model, adapters, training config, and generation settings.
+
+## Features
+- LoRA adapters applied to attention and MLP blocks  
+- Minimal training overhead with notebook-friendly resource use  
+- Drop-in loading for inference or further fine-tuning  
+
+## Requirements
+```bash
+pip install transformers accelerate peft datasets bitsandbytes
+```
+
+## Training
+
+Start training with:
+
+```bash
+accelerate launch train.py --config config.yaml
+```
+
+## Inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base = "mistral-base"
+lora = "./lora-out"
+
+tok = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
+model = PeftModel.from_pretrained(model, lora)
+
+prompt = "Your prompt here"
+out = model.generate(
+    **tok(prompt, return_tensors="pt").to(model.device),
+    max_new_tokens=256
+)
+print(tok.decode(out[0]))
+```
+
+## Files
+- `config.yaml` – training + LoRA configuration  
+- `train.py` – simple training harness  
+- `lora-out/` – adapter weights after training  
+- `generation_config.json` – generation defaults  
+- `tokenizer_config.json` / `special_tokens_map.json` – tokenizer metadata  
+
+## License
+MIT

chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": null,
+  "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,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "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,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

config.yaml

@@ -0,0 +1,45 @@
+# Base model + tokenizer
+model_name: "mistral-base"
+tokenizer_name: "mistral-base"
+
+lora:
+  r: 32
+  alpha: 64
+  dropout: 0.05
+  target_modules:
+    - "q_proj"
+    - "k_proj"
+    - "v_proj"
+    - "o_proj"
+    - "gate_proj"
+    - "up_proj"
+    - "down_proj"
+
+training:
+  output_dir: "./lora-out"
+  batch_size: 4
+  micro_batch_size: 1
+  gradient_accumulation_steps: 4
+  learning_rate: 2e-4
+  weight_decay: 0.0
+  warmup_ratio: 0.03
+  num_epochs: 3
+  max_grad_norm: 1.0
+  fp16: true
+
+dataset:
+  path: "./data"
+  field: "text"
+  shuffle: true
+  num_workers: 4
+
+generation:
+  bos_token_id: 1
+  eos_token_id: 2
+  max_new_tokens: 256
+  temperature: 0.7
+  top_p: 0.9
+
+logging:
+  steps: 10
+  save_steps: 200

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1acc43f03937c7664bdf5f560e1e9992b44fd4066e6b289d8fed990e9c722f0
+size 4450837496

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}