Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- tyson0420/alpaca_codellama
+- tyson0420/stack-codellama-fil-python
+---
+
+# codellama-7B-instruct-passthrough
+
+codellama-7B-instruct-passthrough is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [tyson0420/alpaca_codellama](https://huggingface.co/tyson0420/alpaca_codellama)
+* [tyson0420/stack-codellama-fil-python](https://huggingface.co/tyson0420/stack-codellama-fil-python)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: tyson0420/alpaca_codellama
+      layer_range: [0, 32]
+  - sources:
+    - model: tyson0420/stack-codellama-fil-python
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "tyson0420/alpaca_codellama",
+  "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": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+
+slices:
+  - sources:
+    - model: tyson0420/alpaca_codellama
+      layer_range: [0, 32]
+  - sources:
+    - model: tyson0420/stack-codellama-fil-python
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7831e7bcb76ae11cae34da5befcc82d8588e3ff45434cf794a93af21479110
+size 1933644544

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92dc9bad344eed43ff607c48cb8cf4ee5b595c6420d46f93efa88f2610303b11
+size 1933644544

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddcd07c72bb55f7f9a26462f1819b1b18856ab09550f677d050148493dbd743
+size 1933661136

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfe8e3b9381452087e169f0558e7e94e2e538713583610cf7bbac57fc021be0
+size 1933661136

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca9c38744f525e5f87139f4e22979ffa9e776e84bb96400b847476f259a3224
+size 1971507280

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd9d82b0446546620fa1da34cdbcd49ece5ffb1c39a1de707a5c7750bb649f4
+size 1971507280

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129f70825292befd0b668b1c3fbd90fd9d050ecd46d428f22569f6aacb49a648
+size 1933661192

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865ea0d27ae1c154a8a66b7fdbe2983eb97f91fab93cbef680a257097b2eea6c
+size 1933661192

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129744e126718b15e3cfb89b64bc232fa3ef2ab90d6289c400306695765916b
+size 1933661184

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1aa727a6421dfde26995382f40c3b76c57355bb7b5f48f5e3df941196f7aee
+size 1933661184

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5140ed6793d77ec1a63197378ca709b82aa5d621b4698f6662d4e0ede7d5060
+size 1994609056

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fac6f1ac6bf6358869893816292f28c21840d17cc44316c4b0983508140ae2
+size 1994609056

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8208356347e2c3806bdc4fe5fe0db382c67f85eb8ae49ce6a5ffea057b90db1
+size 1776382728

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd74031712ee7661c870aca8db12d81a70aae0f3a3bb1065df5b21249c95693
+size 1990284296

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192f3e503136359cab32f347487df6c010ac0a8e749222018f73616106420c3b
+size 1990284296

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a3134e05886d6ba157bc90cbe15db248889c29b49037958a04dfe261eb3c18
+size 1033956288

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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
+  },
+  "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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "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
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}