SJ-Donald commited on
Commit
4794c86
1 Parent(s): 6e8273e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - LDCC/LDCC-SOLAR-10.7B
8
+ - upstage/SOLAR-10.7B-Instruct-v1.0
9
+ ---
10
+
11
+ # SOLAR-10.7B-slerp
12
+
13
+ SOLAR-10.7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B)
15
+ * [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: LDCC/LDCC-SOLAR-10.7B
23
+ layer_range: [0, 48]
24
+ - model: upstage/SOLAR-10.7B-Instruct-v1.0
25
+ layer_range: [0, 48]
26
+ merge_method: slerp
27
+ base_model: upstage/SOLAR-10.7B-Instruct-v1.0
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
+ tokenizer_source: union
36
+ dtype: float16
37
+
38
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
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": 14336,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 48,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.35.2",
26
+ "use_cache": true,
27
+ "vocab_size": 48000
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: LDCC/LDCC-SOLAR-10.7B
5
+ layer_range: [0, 48]
6
+ - model: upstage/SOLAR-10.7B-Instruct-v1.0
7
+ layer_range: [0, 48]
8
+ merge_method: slerp
9
+ base_model: upstage/SOLAR-10.7B-Instruct-v1.0
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
+ tokenizer_source: union
18
+ dtype: float16
19
+
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58a7c11d71e9904e449f38e1e528d3895a46b3185a5fe2da3cf9541c8b7bc32
3
+ size 1903226688
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186d10d2489e113f7c1d1624645fd02b67100f142f5057085ff718fe96af0acf
3
+ size 1979781384
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2d0b5956eb4a57d65ca6262f2a1a9c2456906d335dc10ab18210266a222abc
3
+ size 1979798000
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d6b63ca2c82669c9569466c0c878d02855b3f50da2c3454093d7807b7d3fc0
3
+ size 1946243952
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674fa6526945460b30ff0f973805dc214efa9e0f39954478de0e018c09e9918a
3
+ size 1988161840
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ea3fc3a2dd7a449b2841a790fe0339705db82fb9ef31e1cf23d91ff4db0bd6
3
+ size 1937863520
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883d441ade2706614988156aacb98a2f338fd7edecfb2679fb995415c5e125e1
3
+ size 1979781416
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131a02e1807bcf840683d5831d79bfa4bccd664201dff4b1a4a25e89329d45d3
3
+ size 1946243952
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e3fe38a54d7ca515744b69d26c9a68fdd97ead85dd699dfc2725eb93b7231b
3
+ size 1979781416
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5c17d1193bc7ccf7d9716c7ec0dba2268be548738bee4d40165c70f1c2deca
3
+ size 1946235648
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c227661b03fee6922f0eebfa9a72d048b5880dcd2858f9eaddf8fc38135c6f5
3
+ size 1936780784
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59546a69ca69db60aee15a37975b1c6044e83c9493b0ae2edfab10d111301e7
3
+ size 201343792
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "lm_head.weight": "model-00011-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff