updating model files

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "OpenLMModel"
+  ],
+  "model_type": "openlm",
+  "params": null,
+  "params_args_dict": {
+    "apply_qk_norm": true,
+    "attn_activation": null,
+    "attn_name": "auto",
+    "attn_seq_scalar": null,
+    "attn_seq_scalar_alpha": null,
+    "dim": 2048,
+    "ffn_type": "swiglu_torch",
+    "model": "open_lm_1b_swiglutorch",
+    "model_norm": "gain_only_lp_layer_norm",
+    "moe_capacity_factor": 1.25,
+    "moe_expert_model_parallelism": false,
+    "moe_freq": 0,
+    "moe_loss_weight": 0.1,
+    "moe_num_experts": null,
+    "moe_top_k": 2,
+    "moe_weight_parallelism": false,
+    "n_heads": 16,
+    "n_layers": 24,
+    "norm_eps": 1e-05,
+    "positional_embedding_type": "rotary",
+    "post_embed_norm": false,
+    "qk_norm": true,
+    "seq_len": 2048,
+    "vocab_size": 50432,
+    "weight_tying": false
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:719dade9dd8fa498a2b18f606b7bf132537b292a12f468bdcd2f13aac76324b2
+size 4985679432

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c97e641a4f57c84bae3ab74c3ef762065994493f6889efe08baa830ea2fc8d7
+size 773925424

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 5759580160
+  },
+  "weight_map": {
+    "model.layers.0.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attention.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.pos_embed.inv_freq": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w12.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.pos_embed.inv_freq": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w12.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.output.weight": "model-00002-of-00002.safetensors",
+    "model.tok_embeddings.weight": "model-00001-of-00002.safetensors"
+  }
+}