Upload folder using huggingface_hub

README.md

@@ -0,0 +1,110 @@
+---
+library_name: transformers.js
+license: apache-2.0
+datasets:
+- HuggingFaceH4/ultrachat_200k
+language:
+- en
+base_model:
+- Felladrin/Minueza-2-96M-Instruct-Variant-10
+tags:
+- llama-factory
+pipeline_tag: text-generation
+---
+
+
+
+# Minueza-2-96M-Instruct-Variant-10 (ONNX)
+
+
+This is an ONNX version of [Felladrin/Minueza-2-96M-Instruct-Variant-10](https://huggingface.co/Felladrin/Minueza-2-96M-Instruct-Variant-10). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
+
+
+## Usage with Transformers.js
+
+
+See the pipeline documentation for `text-generation`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextGenerationPipeline
+
+
+---
+
+
+# Minueza-2-96M-Instruct (Variant 10)
+
+This model is a fine-tuned version of [Felladrin/Minueza-2-96M](https://huggingface.co/Felladrin/Minueza-2-96M) on the English [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) 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-10",
+    device=torch.device("cuda" if torch.cuda.is_available() else "cpu"),
+)
+
+messages = [
+  {
+    "role": "system",
+    "content": "You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.",
+  },
+  {
+    "role": "user",
+    "content": "Hi!",
+  },
+  {
+    "role": "assistant",
+    "content": "Hello! How can I help you?",
+  },
+  {
+    "role": "user",
+    "content": "I am interested in developing a career in software engineering. Do you have any suggestions?",
+  },
+]
+
+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 +1,31 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Felladrin/Minueza-2-96M-Instruct-Variant-10",
+  "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-06,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.49.0"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2dbcc40e8eb5f9f475a171aff85b679b07f6a7e68fae70963238812a5e00c8
+size 384240317

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee324dee78b4b4ce1f7307e71037716f31ae3a0b8759c6f4e5db18bb6570ead6
+size 128190351

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c1d9a241409e81a2d3784552c2ade38d275cb3a640815a4c3afebbfc631e65
+size 192230262

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cf845c1d227ffa1e5cc3621ac5a520f78a4f1346cf26f0b4d2cb2f85752c85
+size 96320555

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7e3038b88b08a9a5aca6add207ee30b7da6bbf34012a7b7b2b6b20a71feff9
+size 132845545

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcf34f106c53f49a2adfb5f5e6af98e876667f359d81088c1d4c146a5cda9d3
+size 85159553

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cf845c1d227ffa1e5cc3621ac5a520f78a4f1346cf26f0b4d2cb2f85752c85
+size 96320555

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3a414d1504c8c86368b496f144c7b9bd0a67c55350fc97b58c1219f2260767
+size 96320586

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": false,
+    "reduce_range": false,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}