Upload folder using huggingface_hub

.gitattributes

@@ -44,3 +44,5 @@ gemma-3-1b-it-int8-v1/gemma-3-1b-it-int8-v1.cellm filter=lfs diff=lfs merge=lfs
 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
+gemma-4-E2B-it-int4-aggr-v5/gemma-4-E2B-it-int4-aggr-v5.cellmd filter=lfs diff=lfs merge=lfs -text
+gemma-4-E2B-it-int4-aggr-v5/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gemma-4-E2B-it-int4-aggr-v5/README.md

@@ -0,0 +1,37 @@
+# gemma-4-E2B-it-int4-aggr-v5 (cellm)
+
+## Files
+
+- `gemma-4-E2B-it-int4-aggr-v5.cellmd` (~3.3GB)
+- `tokenizer.json`
+- `tokenizer_config.json`
+
+## Run (CPU)
+
+```bash
+cd /cellm
+./target/release/infer \
+  --model models/to-huggingface/gemma-4-E2B-it-int4-aggr-v5/gemma-4-E2B-it-int4-aggr-v5.cellmd \
+  --tokenizer models/to-huggingface/gemma-4-E2B-it-int4-aggr-v5/tokenizer.json \
+  --prompt "What is consciousness?" \
+  --chat --chat-format auto \
+  --gen 48 \
+  --temperature 0 \
+  --backend cpu \
+  --kv-encoding f16
+```
+
+## Run (Metal)
+
+```bash
+cd /cellm
+./target/release/infer \
+  --model models/to-huggingface/gemma-4-E2B-it-int4-aggr-v5/gemma-4-E2B-it-int4-aggr-v5.cellmd \
+  --tokenizer models/to-huggingface/gemma-4-E2B-it-int4-aggr-v5/tokenizer.json \
+  --prompt "What is consciousness?" \
+  --chat --chat-format auto \
+  --gen 48 \
+  --temperature 0 \
+  --backend metal \
+  --kv-encoding turboquant
+```

gemma-4-E2B-it-int4-aggr-v5/gemma-4-E2B-it-int4-aggr-v5.cellmd

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54cf219d4da3c50efe03f10841b0bac572b164ab1c61020d9fa6143ab11b90a
+size 3591368768

gemma-4-E2B-it-int4-aggr-v5/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

gemma-4-E2B-it-int4-aggr-v5/tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "type": "object",
+    "properties": {
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "content": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
+        "type": "array",
+        "items": {
+          "type": "object",
+          "properties": {
+            "type": {
+              "const": "function"
+            },
+            "function": {
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
+              "properties": {
+                "name": {
+                  "type": "string"
+                },
+                "arguments": {
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call",
+                  "additionalProperties": {}
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}