Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+license: apache-2.0
+datasets:
+  - WizardLMTeam/WizardLM_evol_instruct_V2_196k
+language:
+  - en
+base_model:
+  - Felladrin/Minueza-2-96M
+tags:
+  - llama-factory
+---
+
+# Minueza-2-96M-Instruct (Variant 06)
+
+This model is a fine-tuned version of [Felladrin/Minueza-2-96M](https://huggingface.co/Felladrin/Minueza-2-96M) on the English [WizardLMTeam/WizardLM_evol_instruct_V2_196k](https://huggingface.co/datasets/WizardLMTeam/WizardLM_evol_instruct_V2_196k) dataset.
+
+## Usage
+
+```sh
+pip install transformers==4.51.1 torch==2.6.0
+```
+
+```python
+from transformers import pipeline, TextStreamer
+import torch
+
+generate_text = pipeline(
+    "text-generation",
+    model="Felladrin/Minueza-2-96M-Instruct-Variant-06",
+    device=torch.device("cuda" if torch.cuda.is_available() else "cpu"),
+)
+
+messages = [
+  {
+    "role": "user",
+    "content": "Summarize the advantages of internet marketing.",
+  },
+]
+
+generate_text(
+    generate_text.tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    ),
+    streamer=TextStreamer(generate_text.tokenizer, skip_special_tokens=True),
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+    top_k=0,
+    min_p=0.1,
+    repetition_penalty=1.17,
+)
+```
+
+## Training hyperparameters
+
+The following hyperparameters were used during training:
+
+- learning_rate: 5.8e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+## Framework versions
+
+- Transformers 4.51.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.0
+
+## License
+
+This model is licensed under the Apache License 2.0.

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": ["LlamaForCausalLM"],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 56,
+  "hidden_act": "silu",
+  "hidden_size": 672,
+  "initializer_range": 0.02,
+  "intermediate_size": 2688,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-6,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8707447a0c4011828153d893ee88a164d58f94166ca3530f486bcc7de5ebac91
+size 192018920

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a highly knowledgeable and friendly assistant. Your goal is to understand and respond to user inquiries with clarity. Your interactions are always respectful, helpful, and focused on delivering the most accurate information to the user.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}