AbdallahElsaadany commited on
Commit
481a342
β€’
1 Parent(s): 761bcaf

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - defog/sqlcoder-7b-2
8
+ - codellama/CodeLlama-7b-hf
9
+ ---
10
+
11
+ # sqlllama
12
+
13
+ sqlllama is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2)
15
+ * [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: defog/sqlcoder-7b-2
23
+ layer_range: [0, 32]
24
+ - model: codellama/CodeLlama-7b-hf
25
+ layer_range: [0, 32]
26
+ merge_method: slerp
27
+ base_model: codellama/CodeLlama-7b-hf
28
+ parameters:
29
+ t:
30
+ - filter: self_attn
31
+ value: [0, 0.5, 0.3, 0.7, 1]
32
+ - filter: mlp
33
+ value: [1, 0.5, 0.7, 0.3, 0]
34
+ - value: 0.5
35
+ dtype: bfloat16
36
+
37
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codellama/CodeLlama-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.38.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32016
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: defog/sqlcoder-7b-2
5
+ layer_range: [0, 32]
6
+ - model: codellama/CodeLlama-7b-hf
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: codellama/CodeLlama-7b-hf
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.5
17
+ dtype: bfloat16
18
+
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6dd6f8f834d889afc3613bbb37e28490e0456e7814428b376096e09fe36c7d
3
+ size 1933644544
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6991d37233ab9f8e42d911047715d1c891834b8bee9bf939e3b082fb9dc512f
3
+ size 1933661136
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f810ae86e1f15a947d5ab13f4e679d2015b38a2b657040fbd26b67ed1dc6f81
3
+ size 1971507280
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819adb56c5a6627f223f781f2b6298196bc1b2cbfef341664d04216dac50e943
3
+ size 1933661192
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c562cbdc1a206b7f915664d49cde4438b4931b2df8dc26dc49a11811ac0ca37
3
+ size 1933661184
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcc7043b32eb566e58df43d0c535111d501b1a65a4f11fad1eeba5e4aa35401
3
+ size 1994609056
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cdc72155344dd4f866fb2a5de129b9a42c1aa0e4fd4e3c162421f9bc205c72f
3
+ size 1776382728
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.embed_tokens.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00006-of-00007.safetensors", "model.norm.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "eot_token": "▁<EOT>",
72
+ "fill_token": "<FILL_ME>",
73
+ "legacy": null,
74
+ "middle_token": "▁<MID>",
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": null,
77
+ "prefix_token": "▁<PRE>",
78
+ "sp_model_kwargs": {},
79
+ "suffix_token": "▁<SUF>",
80
+ "tokenizer_class": "CodeLlamaTokenizer",
81
+ "unk_token": "<unk>",
82
+ "use_default_system_prompt": false
83
+ }