Add weights

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,10 @@
 ---
 license: apache-2.0
+base_model: soob3123/amoral-gemma3-1B-v2
+base_model_relation: quantized
+library_name: mlc-llm
+pipeline_tag: text-generation
 ---
+
+4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [amoral-gemma3-1B-v2](https://huggingface.co/soob3123/amoral-gemma3-1B-v2) for inference with the [Private LLM](http://privatellm.app) app.
+

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,5 @@
+{
+  "quantization_config": {
+        "bits": 4
+    }
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4917a670473e45b676f9d6a1e2789ad4d66e4bd23bacbd5f0a10d06194995ae5
+size 603979776

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043b4f7dd461bd6a22592f9d7e2d9d1218a1bbf8c16e10ccbd0130ed724d49fb
+size 31804160

params_shard_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2268b160144df94ae1f73851a55b8a6af528d99a59e157b4fc6af8829af8c64
+size 27696128

params_shard_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0082af8f6f1ca70b5fdd7e8bad3e5818ba2a7ed3134625b8995db4a57a2dfd
+size 27696128

params_shard_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602e8ffa01aa3d92b4e1e5df33ec211ce58dccd41a1abc8155f472c577186484
+size 27696128

params_shard_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e8e015270bff5240961cda4c32303a97b338e054af9223410b123be53b32f4
+size 23590400

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb028487569125f0d5375679342bd62f19bbeb89824458a594509172358c2df
+size 27696128

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2884ce5bb11310bbc83d8a1bde4be943d354585ee3f2369fe7fff444f93b7547
+size 27696128

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fab3bf6f4480c154cd7be9c8ef74ff274b7a2c2ff266177862bbd571c0d8de5
+size 27696128

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bcec3c830dd49d338c70151f2f5c26588d5dd3a29ec4b7aabdbcacfd419d9b
+size 27696128

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296e93c517bea4631d52d281d7c12e7acdd1bae1cc413d0483ff187f9d4c9e08
+size 27696128

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c378daaf3c79a6db768644bc5cb9151ccd0df0237ecc4a83cbf8ee32116955
+size 27696128

params_shard_8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc4928c0b24292f8a10209da7660479ff6318e097107d15f2b624541b300ee9
+size 27696128

params_shard_9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18e1393dd5915faca94a00e0cb10cdfa00ae3c25a36c159c482c58b5660a3e6
+size 27696128

private-llm-config.json

@@ -0,0 +1,81 @@
+{
+  "model_type": "gemma3_text",
+  "quantization": "w4a16g128asym_1",
+  "model_config": {
+    "text_config": {
+      "hidden_size": 1152,
+      "intermediate_size": 6912,
+      "num_hidden_layers": 26,
+      "attention_bias": false,
+      "num_attention_heads": 4,
+      "num_key_value_heads": 1,
+      "head_dim": 256,
+      "rms_norm_eps": 1e-06,
+      "hidden_activation": "gelu_pytorch_tanh",
+      "position_embedding_base": 1000000,
+      "rope_local_base_freq": 10000,
+      "sliding_window_pattern": 6,
+      "context_window_size": 8192,
+      "prefill_chunk_size": 8192,
+      "query_pre_attn_scalar": 256,
+      "sliding_window": 512,
+      "kwargs": {
+        "architectures": [
+          "Gemma3ForCausalLM"
+        ],
+        "attention_dropout": 0.0,
+        "attn_logit_softcapping": null,
+        "bos_token_id": 2,
+        "cache_implementation": "hybrid",
+        "eos_token_id": 106,
+        "final_logit_softcapping": null,
+        "initializer_range": 0.02,
+        "max_position_embeddings": 32768,
+        "model_type": "gemma3_text",
+        "pad_token_id": 0,
+        "rope_scaling": null,
+        "rope_theta": 1000000,
+        "torch_dtype": "bfloat16",
+        "transformers_version": "4.50.0.dev0",
+        "unsloth_fixed": true,
+        "unsloth_version": "2025.3.18",
+        "use_cache": true
+      }
+    },
+    "vocab_size": 262144,
+    "tensor_parallel_shards": 1,
+    "max_batch_size": 80,
+    "context_window_size": 32768,
+    "sliding_window_size": -1,
+    "prefill_chunk_size": 128,
+    "is_text_model": true
+  },
+  "vocab_size": 262144,
+  "context_window_size": 32768,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 128,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "mean_gen_len": 128,
+  "max_gen_len": 512,
+  "shift_fill_factor": 0.3,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.0,
+  "top_p": 0.95,
+  "conv_template": "gemma3_instruction",
+  "pad_token_id": 0,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "tokenizer_files": [
+    "tokenizer.model",
+    "tokenizer.json",
+    "added_tokens.json",
+    "tokenizer_config.json"
+  ],
+  "version": "0.1.0"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074