Upload folder using huggingface_hub

README.md

@@ -0,0 +1,47 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# boreas-10_7b
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* boreas-7b-0-16
+* boreas-7b-16-32
+* boreas-7b-0-8-16-24
+* boreas-7b-8-16-24-32
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: boreas-7b-0-16
+      layer_range: [0, 16]
+  - sources:
+    - model: boreas-7b-0-8-16-24
+      layer_range: [0, 8]
+  - sources:
+    - model: boreas-7b-8-16-24-32
+      layer_range: [0, 8]
+  - sources:
+    - model: boreas-7b-16-32
+      layer_range: [0, 16]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "boreas-7b-0-16",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    "sp",
+    "tp",
+    null
+  ],
+  "attn_mechanism": "normal",
+  "axis_dims": [
+    1,
+    -1,
+    1,
+    1
+  ],
+  "axis_names": [
+    "dp",
+    "fsdp",
+    "tp",
+    "sp"
+  ],
+  "backend": null,
+  "bias_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    null,
+    null,
+    null
+  ],
+  "bits": null,
+  "block_b": 1,
+  "block_k": 128,
+  "block_k_dkv": 128,
+  "block_k_dq": 128,
+  "block_k_major": 128,
+  "block_k_major_dkv": 128,
+  "block_k_major_dq": 128,
+  "block_q": 128,
+  "block_q_dkv": 128,
+  "block_q_dq": 128,
+  "block_q_major_dkv": 128,
+  "bos_token_id": 1,
+  "easy_method": "train",
+  "eos_token_id": 2,
+  "generation_attention_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    null,
+    "tp",
+    null
+  ],
+  "generation_bias_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    null,
+    null,
+    null
+  ],
+  "generation_query_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    "sp",
+    null,
+    null
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "key_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    "sp",
+    "tp",
+    null
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "number_rep_kv": 1,
+  "query_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    "sp",
+    "tp",
+    null
+  ],
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "scan_attention_layers": false,
+  "scan_mlp_chunk_size": 1024,
+  "scan_ring_attention": false,
+  "shard_attention_computation": true,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_scan_mlp": false,
+  "use_sharded_kv_caching": true,
+  "use_sharding_constraint": false,
+  "value_partition_spec": [
+    [
+      "dp",
+      "fsdp"
+    ],
+    "sp",
+    "tp",
+    null
+  ],
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+slices:
+  - sources:
+    - model: boreas-7b-0-16
+      layer_range: [0, 16]
+  - sources:
+    - model: boreas-7b-0-8-16-24
+      layer_range: [0, 8]
+  - sources:
+    - model: boreas-7b-8-16-24-32
+      layer_range: [0, 8]
+  - sources:
+    - model: boreas-7b-16-32
+      layer_range: [0, 16]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01abd1242140114560dbd8ee22a1cdc113671dd6c5c67e0eef89207f5a600e95
+size 4886555312

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93380b685dbc20b57af242c42f142c871c3461b1d64810c15b1c12b5645c3380
+size 4949470256

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631b006cadc126d8ccf926f520c0dbdcbb892e6b6723c857066acf93ec803579
+size 4999819328

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5d7d156fac92b74751c29b856f1b73b0f005fcc0e6769a8de3f55f6a97cd07
+size 4999802720

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a763fa5cfe6f14a23f18821378a324c4062cc1153c545fa33453fe8c027f7707
+size 1627451232

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21463048192}, "weight_map": {"lm_head.weight": "model-00001-of-00005.safetensors", "model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}