hflog Aabbhishekk commited on
Commit
4f854be
0 Parent(s):

Duplicate from Aabbhishekk/llama2-7b-function-calling-slerp

Browse files

Co-authored-by: Srivastava <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - meta-llama/Llama-2-7b-hf
8
+ - Trelis/Llama-2-7b-chat-hf-function-calling-v3
9
+ ---
10
+
11
+ # llama2-7b-function-calling-slerp
12
+
13
+ llama2-7b-function-calling-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
15
+ * [Trelis/Llama-2-7b-chat-hf-function-calling-v3](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v3)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: meta-llama/Llama-2-7b-hf
23
+ layer_range: [0, 32]
24
+ - model: Trelis/Llama-2-7b-chat-hf-function-calling-v3
25
+ layer_range: [0, 32]
26
+ merge_method: slerp
27
+ base_model: meta-llama/Llama-2-7b-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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.35.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: meta-llama/Llama-2-7b-hf
5
+ layer_range: [0, 32]
6
+ - model: Trelis/Llama-2-7b-chat-hf-function-calling-v3
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: meta-llama/Llama-2-7b-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 sha256:35e02449afa658efc2e1bd595b963d0fa1aab5890aa751e1ff8a5c5b17e5aa94
3
+ size 1933652888
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64eb6b0798dcdecca3f6e6aed34e802253f4e756ec108083481ad32948a5358
3
+ size 1933661192
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e139346fb7c82b7bd19c403918e2c6155064c58658eb1b4b2bdeb67cb3473e
3
+ size 1933661176
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4c1030b2f916edddb17147fb338cc6d6093f811bf3afb1604eca8578296968
3
+ size 1990275936
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80eaa9fba3e2e741f11a5b229d8f9d06d5fa67166721bfc26b1b00dce497b54a
3
+ size 1923175144
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7145e32805455bae48302abf40494a4c38bce7db3f1c7b30cc59f59e34ab0471
3
+ size 1963003976
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d1bbcc9acb28fb47ccf9b2e95f92cdf09d41f8d7c618e97f38f76a0ca242c1
3
+ size 1799434672
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.embed_tokens.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.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.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.input_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.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.input_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.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_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-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.input_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.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.input_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.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.input_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.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.input_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.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "legacy": false,
32
+ "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": null,
34
+ "padding_side": "right",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "LlamaTokenizer",
37
+ "unk_token": "<unk>",
38
+ "use_default_system_prompt": false
39
+ }