初始化项目，由ModelHub XC社区提供模型

Model: Shubhankar444/smolified-ingredient-extractor Source: Original Platform
2026-05-30 16:44:21 +08:00
commit f24df4b1ab
7 changed files with 247 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- text-generation-inference
+- transformers
+- smolify
+- dslm
+pipeline_tag: text-generation
+inference:
+  parameters:
+    temperature: 1
+    top_p: 0.95
+    top_k: 64
+---
+
+# 🤏 smolified-ingredient-extractor
+
+> **Intelligence, Distilled.**
+
+This is a **Domain Specific Language Model (DSLM)** generated by the **Smolify Foundry**.
+
+It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.
+
+## 📦 Asset Details
+- **Origin:** Smolify Foundry (Job ID: `22fdd899`)
+- **Architecture:** gemma-3-270m
+- **Training Method:** Proprietary Neural Distillation
+- **Optimization:** 4-bit Quantized / FP16 Mixed
+- **Dataset:** [Link to Dataset](https://huggingface.co/datasets/Shubhankar444/smolified-ingredient-extractor)
+
+## 🚀 Usage (Inference)
+This model is compatible with standard inference backends like vLLM, and Hugging Face Transformers.
+
+```python
+# Example: Running your Sovereign Model
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Shubhankar444/smolified-ingredient-extractor"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+
+messages = [
+    {"role": "system", "content": '''Extract ingredients from the Indian recipe and return as a Python list.'''},
+    {"role": "user", "content": '''Prepare Bhindi Masala by slicing okra and shallow frying in vegetable oil. Keep aside. In the same pan, saute onions and tomatoes with cumin, coriander powder, dry mango powder, and salt. Add the okra back in and toss well until the vegetables are soft. Serve with hot roti.'''}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize = False,
+    add_generation_prompt = True,
+)
+if "gemma-3-270m" == "gemma-3-270m":
+    text = text.removeprefix('<bos>')
+
+from transformers import TextStreamer
+_ = model.generate(
+    **tokenizer(text, return_tensors = "pt").to(model.device),
+    max_new_tokens = 1000,
+    temperature = 1.0, top_p = 0.95, top_k = 64,
+    streamer = TextStreamer(tokenizer, skip_prompt = True),
+)
+```
+
+## ⚖️ License & Ownership
+This model weights are a sovereign asset owned by **Shubhankar444**.
+Generated via [Smolify.ai](https://smolify.ai).
+
+[<img src="https://smolify.ai/smolify.gif" width="100"/>](https://smolify.ai)
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,64 @@
+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 106,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 640,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_name": "unsloth/gemma-3-270m-it",
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+        "full_attention": {
+            "rope_theta": 1000000.0,
+            "rope_type": "default"
+        },
+        "sliding_attention": {
+            "rope_theta": 10000.0,
+            "rope_type": "default"
+        }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.3.11",
+    "use_bidirectional_attention": false,
+    "use_cache": false,
+    "vocab_size": 262144
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9da2528aafe9ebcdcf6b8ab811664079a0e4bb0547f874273235977d9d6f6b
+size 536223056
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,25 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{ '<start_of_turn>model\n' }}\n{%- endif -%}\n"
+}