Add files using upload-large-folder tool

README.md

@@ -1,10 +1,18 @@
 ---
+base_model: google/gemma-3-270m-it
 license: gemma
-pipeline_tag: text-generation
 tags:
+- gemma3
+- gemma
+- google
 - mlx
-base_model: google/gemma-3-270m-it
+pipeline_tag: text-generation
 library_name: mlx
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
+  agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
 ---
 
 # mlx-community/gemma-3-270m-it-4bit

added_tokens.json

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

config.json

@@ -7,7 +7,7 @@
     "attention_dropout": 0.0,
     "attn_logit_softcapping": null,
     "bos_token_id": 2,
-    "eos_token_id": [1, 106],
+    "eos_token_id": 1,
     "final_logit_softcapping": null,
     "head_dim": 256,
     "hidden_activation": "gelu_pytorch_tanh",
@@ -40,14 +40,6 @@
     "num_hidden_layers": 18,
     "num_key_value_heads": 1,
     "pad_token_id": 0,
-    "quantization": {
-        "group_size": 64,
-        "bits": 4
-    },
-    "quantization_config": {
-        "group_size": 64,
-        "bits": 4
-    },
     "query_pre_attn_scalar": 256,
     "rms_norm_eps": 1e-06,
     "rope_local_base_freq": 10000.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f636d234aec7387e2ec59da122f36681b8e6bfd7ac9ae88f9721ea11260794f
-size 245312212
+oid sha256:1404199e25dfbb61f50a99382cf70dff5bfc4529f2ad350d1bf278bf4d4d34b0
+size 871767180

model.safetensors.index.json

@@ -1,500 +1,244 @@
 {
     "metadata": {
-        "total_size": 245257472,
+        "total_size": 871740672,
         "total_parameters": 435870336
     },
     "weight_map": {
-        "lm_head.biases": "model.safetensors",
-        "lm_head.scales": "model.safetensors",
         "lm_head.weight": "model.safetensors",
-        "model.embed_tokens.biases": "model.safetensors",
-        "model.embed_tokens.scales": "model.safetensors",
         "model.embed_tokens.weight": "model.safetensors",
         "model.layers.0.input_layernorm.weight": "model.safetensors",
-        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
         "model.layers.0.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
         "model.layers.0.mlp.up_proj.weight": "model.safetensors",
         "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.1.input_layernorm.weight": "model.safetensors",
-        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
         "model.layers.1.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
         "model.layers.1.mlp.up_proj.weight": "model.safetensors",
         "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.10.input_layernorm.weight": "model.safetensors",
-        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
         "model.layers.10.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
         "model.layers.10.mlp.up_proj.weight": "model.safetensors",
         "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.11.input_layernorm.weight": "model.safetensors",
-        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
         "model.layers.11.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
         "model.layers.11.mlp.up_proj.weight": "model.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.12.input_layernorm.weight": "model.safetensors",
-        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
         "model.layers.12.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
         "model.layers.12.mlp.up_proj.weight": "model.safetensors",
         "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.13.input_layernorm.weight": "model.safetensors",
-        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
         "model.layers.13.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
         "model.layers.13.mlp.up_proj.weight": "model.safetensors",
         "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.14.input_layernorm.weight": "model.safetensors",
-        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
         "model.layers.14.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
         "model.layers.14.mlp.up_proj.weight": "model.safetensors",
         "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.15.input_layernorm.weight": "model.safetensors",
-        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
         "model.layers.15.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
         "model.layers.15.mlp.up_proj.weight": "model.safetensors",
         "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.16.input_layernorm.weight": "model.safetensors",
-        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
         "model.layers.16.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
         "model.layers.16.mlp.up_proj.weight": "model.safetensors",
         "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.17.input_layernorm.weight": "model.safetensors",
-        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
         "model.layers.17.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
         "model.layers.17.mlp.up_proj.weight": "model.safetensors",
         "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.2.input_layernorm.weight": "model.safetensors",
-        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
         "model.layers.2.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
         "model.layers.2.mlp.up_proj.weight": "model.safetensors",
         "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.3.input_layernorm.weight": "model.safetensors",
-        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
         "model.layers.3.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
         "model.layers.3.mlp.up_proj.weight": "model.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.4.input_layernorm.weight": "model.safetensors",
-        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
         "model.layers.4.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
         "model.layers.4.mlp.up_proj.weight": "model.safetensors",
         "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.5.input_layernorm.weight": "model.safetensors",
-        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
         "model.layers.5.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
         "model.layers.5.mlp.up_proj.weight": "model.safetensors",
         "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.6.input_layernorm.weight": "model.safetensors",
-        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
         "model.layers.6.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
         "model.layers.6.mlp.up_proj.weight": "model.safetensors",
         "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.7.input_layernorm.weight": "model.safetensors",
-        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
         "model.layers.7.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
         "model.layers.7.mlp.up_proj.weight": "model.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.8.input_layernorm.weight": "model.safetensors",
-        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
         "model.layers.8.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
         "model.layers.8.mlp.up_proj.weight": "model.safetensors",
         "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.9.input_layernorm.weight": "model.safetensors",
-        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
-        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
         "model.layers.9.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
-        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
-        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
-        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
         "model.layers.9.mlp.up_proj.weight": "model.safetensors",
         "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
         "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
-        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
-        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
-        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
-        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
-        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
-        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
-        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
         "model.norm.weight": "model.safetensors"
     }

tokenizer.model

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