Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,150 @@
+---
+pipeline_tag: text-generation
+base_model:
+- google/gemma-3-1b-it
+library_name: transformers.js
+license: gemma
+new_version: onnx-community/gemma-3-1b-it-ONNX-GQA
+---
+
+## Usage
+
+### ONNXRuntime
+
+```py
+from transformers import AutoConfig, AutoTokenizer
+import onnxruntime
+import numpy as np
+
+# 1. Load config, processor, and model
+path_to_model = "./gemma-3-1b-it-ONNX"
+config = AutoConfig.from_pretrained(path_to_model)
+tokenizer = AutoTokenizer.from_pretrained(path_to_model)
+decoder_session = onnxruntime.InferenceSession(f"{path_to_model}/onnx/model.onnx")
+
+## Set config values
+num_key_value_heads = config.num_key_value_heads
+head_dim = config.head_dim
+num_hidden_layers = config.num_hidden_layers
+eos_token_id = 106 # 106 is for <end_of_turn>
+
+# 2. Prepare inputs
+## Create input messages
+messages = [
+  { "role": "system", "content": "You are a helpful assistant." },
+  { "role": "user", "content": "Write me a poem about Machine Learning." },
+]
+
+## Apply tokenizer
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="np")
+
+## Prepare decoder inputs
+batch_size = inputs['input_ids'].shape[0]
+past_key_values = {
+    f'past_key_values.{layer}.{kv}': np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
+    for layer in range(num_hidden_layers)
+    for kv in ('key', 'value')
+}
+input_ids = inputs['input_ids']
+position_ids = np.tile(np.arange(1, input_ids.shape[-1] + 1), (batch_size, 1))
+
+# 3. Generation loop
+max_new_tokens = 1024
+generated_tokens = np.array([[]], dtype=np.int64)
+for i in range(max_new_tokens):
+  logits, *present_key_values = decoder_session.run(None, dict(
+      input_ids=input_ids,
+      position_ids=position_ids,
+      **past_key_values,
+  ))
+
+  ## Update values for next generation loop
+  input_ids = logits[:, -1].argmax(-1, keepdims=True)
+  position_ids = position_ids[:, -1:] + 1
+  for j, key in enumerate(past_key_values):
+    past_key_values[key] = present_key_values[j]
+
+  generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
+  if (input_ids == eos_token_id).all():
+    break
+
+  ## (Optional) Streaming
+  print(tokenizer.decode(input_ids[0]), end='', flush=True)
+print()
+
+# 4. Output result
+print(tokenizer.batch_decode(generated_tokens))
+```
+
+<details>
+<summary>See example output</summary>
+
+```
+Okay, here’s a poem about Machine Learning, aiming for a balance of technical and evocative language:
+
+**The Silent Learner**
+
+The data streams, a boundless flow,
+A river vast, where patterns grow.
+No human hand to guide the way,
+Just algorithms, come what may.
+
+Machine Learning, a subtle art,
+To teach a system, a brand new start.
+With weights and biases, finely tuned,
+It seeks the truth, beneath the moon.
+
+It learns from errors, big and small,
+Adjusting swiftly, standing tall.
+From pixels bright to voices clear,
+It builds a model, banishing fear.
+
+Of blind prediction, cold and stark,
+It finds the meaning, leaves its mark.
+A network deep, a complex grace,
+Discovering insights, time and space.
+
+It sees the trends, the subtle hue,
+Predicting futures, fresh and new.
+A silent learner, ever keen,
+A digital mind, unseen, serene.
+
+So let the code begin to gleam,
+A blossoming of a learning dream. 
+Machine Learning, a wondrous sight,
+Shaping the future, shining bright. 
+
+---
+
+Would you like me to:
+
+*   Adjust the tone or style? (e.g., more technical, more metaphorical)
+*   Focus on a specific aspect of ML (e.g., neural networks, data analysis)?
+*   Create a different length or format?
+```
+
+</details>
+
+
+
+### Transformers.js
+```js
+import { pipeline } from "@huggingface/transformers";
+
+// Create a text generation pipeline
+const generator = await pipeline(
+  "text-generation",
+  "onnx-community/gemma-3-1b-it-ONNX",
+  { dtype: "q4" },
+);
+
+// Define the list of messages
+const messages = [
+  { role: "system", content: "You are a helpful assistant." },
+  { role: "user", content: "Write me a poem about Machine Learning." },
+];
+
+// Generate a response
+const output = await generator(messages, { max_new_tokens: 512, do_sample: false });
+console.log(output[0].generated_text.at(-1).content);
+```

config.json

@@ -0,0 +1,44 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "google/gemma-3-1b-it",
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0.dev0",
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": true
+    }
+  },
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdd6cc5892fb4f3ea04b423657561b437239b37ab963b85bebae4532081a16f
+size 1012725

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f261e3a3b222e3110bd7d07f1a24d3bdcade389df85d163f11c82cfa1182b700
+size 1602007661

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7278853fe0e9babcdaad178c2d91aff09830b510a9ca88317634f0ef8194d19e
+size 2000774696

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8ddeb9c637d43625df45933ad3a9e2337b8a027ab37a70dc230735ba285f5c
+size 1001481982

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd65478ade20f0bea7ed1e80455e3b3b6eb6f4242d611d63e7bcddc94cc0f108
+size 1645616265

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8cb5ab287f04050d29de31e47354f8868069c0dec8cab326376274a6a12508
+size 997769309

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8ddeb9c637d43625df45933ad3a9e2337b8a027ab37a70dc230735ba285f5c
+size 1001481982

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714ab717b4840136b736a3a288f853ac9386751f33c2edd8a753086530cf9dbc
+size 1001482078

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568