Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Suchinthana/Sinhala-Translate-and-Dolly-Llama-7b
+- austinm2151/Llama2-7b-Summarizer
+---
+
+# LLama_passthrough
+
+LLama_passthrough is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [Suchinthana/Sinhala-Translate-and-Dolly-Llama-7b](https://huggingface.co/Suchinthana/Sinhala-Translate-and-Dolly-Llama-7b)
+* [austinm2151/Llama2-7b-Summarizer](https://huggingface.co/austinm2151/Llama2-7b-Summarizer)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: Suchinthana/Sinhala-Translate-and-Dolly-Llama-7b
+      layer_range: [0, 32]
+  - sources:
+    - model: austinm2151/Llama2-7b-Summarizer
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Suchinthana/Sinhala-Translate-and-Dolly-Llama-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+
+slices:
+  - sources:
+    - model: Suchinthana/Sinhala-Translate-and-Dolly-Llama-7b
+      layer_range: [0, 32]
+  - sources:
+    - model: austinm2151/Llama2-7b-Summarizer
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67592a082a7c9dce2f01c01a78d5dc961f08223caa942f975a1b488407c6b0b
+size 1981878800

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3f703e83a07f750718d6233b9e02a07e66fa656f1c4bf76368082011f26a4b
+size 1971401120

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73a5d12f38bbe10298ae41c6672b27755ce1c253ffd0f47cf02b0a24e191db1
+size 1967207424

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4032ce7daeb00bf55596e2abeb863222676e9e158b8323e398bac27ae2b8571
+size 1990292560

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea82ffffaff966d6aa8c17b1b27a14b45036a97c20db1ec1dfa43adeb75b7c4
+size 1956729728

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5738bc7de8ccc02713e875abd9011f6db417b747e1684d41eae560ef410afcf7
+size 1990267672

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e1aeb7aa7b1bfbb81eeb16c90bfb08490051a023ce35c8e879d10f85d67c3b
+size 1933644568

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd621e562efb0a02659c8e83129671a525ee5ff2658fe4585b2af26687937810
+size 1933677792

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66568d6b64ba414ac61024bd66a913d8a9509a039d3cd7ef8d09a94b50b89c00
+size 989907440

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "lm_head.weight": "model-00002-of-00009.safetensors", "model.norm.weight": "model-00002-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}