bluuwhale commited on
Commit
c9c87e4
1 Parent(s): 7521f3c

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Undi95/Toppy-M-7B
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # phase2
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the SLERP merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * [Undi95/Toppy-M-7B](https://huggingface.co/Undi95/Toppy-M-7B)
22
+ * ./merged/phase1
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+
30
+ slices:
31
+ - sources:
32
+ - model: ./merged/phase1
33
+ layer_range: [0, 32]
34
+ - model: Undi95/Toppy-M-7B
35
+ layer_range: [0, 32]
36
+ merge_method: slerp
37
+ base_model: ./merged/phase1
38
+ parameters:
39
+ t:
40
+ - filter: self_attn
41
+ value: [0, 0.5, 0.3, 0.7, 1]
42
+ - filter: mlp
43
+ value: [1, 0.5, 0.7, 0.3, 0]
44
+ - value: 0.5 # fallback for rest of tensors
45
+ dtype: bfloat16
46
+
47
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./merged/phase1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
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": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 100000.0,
20
+ "sliding_window": 16384,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.37.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: ./merged/phase1
5
+ layer_range: [0, 32]
6
+ - model: Undi95/Toppy-M-7B
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: ./merged/phase1
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 # fallback for rest of tensors
17
+ dtype: bfloat16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5129af15d1c81e2e74f054f50ce4c5f3329b20b908c08e90750f0899df8bdc
3
+ size 1889595352
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0057a464d853ff816cd5500db228563f32ba3f6c470abea895b27107a1aedcb3
3
+ size 1979789712
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1d5c57a89839bf9061d4b27d0046c7ef576c6d8acdb19f73494e1325088fb4
3
+ size 1988186784
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f82c49fd1d449db9fd3d5e9fe78459f343108ff07af58a39235dfc1e2ea4213
3
+ size 1937846944
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e521c0c70c6f32a5735d39a5e151939699f5a221a0f96b26d430dd6d37f8a977
3
+ size 1988178496
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfcfb3e6a13efc6f293c43b3f5cbadd6e44bd238d08467fbdb472cbf8a8880e1
3
+ size 1998655576
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9142cd93f73f2abcaf7ba490116d228dce542371dcadf3a42919ff7ad90b51e
3
+ size 1946235664
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf4923c0a0fc7b47f25dfc152b9b985d573ff23c6cc2b4dbc196e9a0a39ca98
3
+ size 755009456
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-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "device_map": {
38
+ "": "cuda"
39
+ },
40
+ "eos_token": "</s>",
41
+ "legacy": true,
42
+ "max_length": 16384,
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "pad_token": null,
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": true
50
+ }