Add gemma-3-1b-it-bnb4

.gitattributes

@@ -38,3 +38,4 @@ gemma-4-2p3b-it-litert/gemma-4-2p3b-it-litert.cellm filter=lfs diff=lfs merge=lf
 gemma-3-1b-it-int8/gemma-3-1b-it-int8.cellmd filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-int8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-4-2p3b-it-litert/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-3-1b-it-bnb4/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma-3-1b-it-bnb4/README.md

@@ -0,0 +1,49 @@
+---
+library_name: cellm
+tags:
+- mobile
+- rust
+- memory-efficient
+- quantized
+- gemma
+---
+
+# Gemma 3 1B IT (4-bit, bitsandbytes)
+
+This folder contains a 4-bit quantized Gemma 3 1B Instruct model package prepared for upload.
+
+## Files
+- `model.safetensors`
+- `config.json`
+- `generation_config.json`
+- `tokenizer.json`
+- `tokenizer_config.json`
+- `chat_template.jinja`
+
+## Model Details
+- **Base model**: `google/gemma-3-1b-it`
+- **Quantization**: 4-bit (bitsandbytes)
+- **On-disk size**: ~952 MB (folder)
+
+## Quick Python Check
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+path = "models/to-huggingface/gemma-3-1b-it-bnb4"
+tok = AutoTokenizer.from_pretrained(path)
+model = AutoModelForCausalLM.from_pretrained(path, device_map="cpu")
+
+msgs = [{"role": "user", "content": "Say hello in one short line."}]
+prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
+inputs = tok(prompt, return_tensors="pt")
+out = model.generate(**inputs, max_new_tokens=24, do_sample=False)
+print(tok.decode(out[0], skip_special_tokens=True))
+```
+
+## Notes
+- This package is in Hugging Face/Transformers-compatible format.
+- If you want a `.cellm` release for this model too, run converter separately and publish as a second artifact.
+
+## License
+Subject to Gemma terms and upstream license constraints.

gemma-3-1b-it-bnb4/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 -%}

gemma-3-1b-it-bnb4/config.json

@@ -0,0 +1,90 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "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,
+  "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",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "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,
+  "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": true,
+    "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"
+  },
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

gemma-3-1b-it-bnb4/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0"
+}

gemma-3-1b-it-bnb4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d1fc799ca03a5900612731f2480ed869681fb6edfa4fdca0679de3625bbab7
+size 964577519

gemma-3-1b-it-bnb4/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

gemma-3-1b-it-bnb4/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}