Upload folder using huggingface_hub

.gitattributes

@@ -43,3 +43,4 @@ qwen2.5-0.5b-int8-v1/qwen2.5-0.5b-int8-v1.cellm filter=lfs diff=lfs merge=lfs -t
 gemma-3-1b-it-int8-v1/gemma-3-1b-it-int8-v1.cellm filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-int8-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-mixed-int4-v1/gemma-3-1b-it-mixed-int4-v1.cellm filter=lfs diff=lfs merge=lfs -text
+smollm2-360m-int8-v1/smollm2-360m-int8-v1.cellm filter=lfs diff=lfs merge=lfs -text

smollm2-360m-int8-v1/README.md

@@ -0,0 +1,48 @@
+---
+library_name: cellm
+tags:
+- mobile
+- rust
+- memory-efficient
+- quantized
+- smollm2
+---
+
+# SmolLM2 360M Instruct (Cellm Int8)
+
+This folder contains a Cellm-converted SmolLM2 360M model and tokenizer assets, ready for publishing to Hugging Face.
+
+## Files
+- `smollm2-360m-int8-v1.cellm`
+- `tokenizer.json`
+- `tokenizer_config.json`
+- `generation_config.json`
+
+## Model Details
+- **Base model**: `HuggingFaceTB/SmolLM2-360M-Instruct`
+- **Format**: `.cellm`
+- **Quantization**: INT8 symmetric weight-only
+- **Size**: ~391 MB
+
+## Usage (Cellm CLI)
+
+```bash
+cd .
+CELLM_LLAMA_ROPE_INTERLEAVED=0 ./target/release/infer \
+  --model models/to-huggingface/smollm2-360m-int8-v1/smollm2-360m-int8-v1.cellm \
+  --tokenizer models/to-huggingface/smollm2-360m-int8-v1/tokenizer.json \
+  --prompt "What is sycophancy?" \
+  --chat \
+  --chat-format auto \
+  --gen 48 \
+  --temperature 0 \
+  --backend metal \
+  --kv-encoding f16
+```
+
+## Notes
+- SmolLM2 requires non-interleaved RoPE in the current Llama runner path. Use `CELLM_LLAMA_ROPE_INTERLEAVED=0`.
+- Tokenizer and generation behavior were cross-checked against Python/Transformers.
+
+## License
+Please follow the original SmolLM2 model license/terms when redistributing weights.

smollm2-360m-int8-v1/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.42.3"
+}

smollm2-360m-int8-v1/smollm2-360m-int8-v1.cellm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6f0b6149efce7160dc08882781e601ba0ee7e5f677aa374239c67ed37ef43f
+size 409685952

smollm2-360m-int8-v1/tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "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
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|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|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}