Aratako commited on
Commit
e885a42
1 Parent(s): 253c056

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,42 @@
1
  ---
2
- license: cc-by-nc-sa-4.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
  ---
9
+ # calm_merged
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 breadcrumbs merge method using I:/llama.cpp/calm3-22b-chat as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * I:/llama.cpp/calm3-22b-RP
22
+
23
+ ### Configuration
24
+
25
+ The following YAML configuration was used to produce this model:
26
+
27
+ ```yaml
28
+ models:
29
+ - model: I:/llama.cpp/calm3-22b-chat
30
+ # no parameters necessary for base model
31
+ - model: I:/llama.cpp/calm3-22b-RP
32
+ parameters:
33
+ weight: 0.5
34
+ merge_method: breadcrumbs
35
+ base_model: I:/llama.cpp/calm3-22b-chat
36
+ dtype: bfloat16
37
+ tokenizer_source: base
38
+ parameters:
39
+ density: 0.9
40
+ gamma: 0.01
41
+
42
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "I:/llama.cpp/calm3-22b-chat",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 65001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 6144,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 16384,
14
+ "max_position_embeddings": 16384,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 48,
18
+ "num_hidden_layers": 48,
19
+ "num_key_value_heads": 48,
20
+ "pad_token_id": 1,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.41.2",
28
+ "use_cache": true,
29
+ "vocab_size": 65003
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: I:/llama.cpp/calm3-22b-chat
3
+ # no parameters necessary for base model
4
+ - model: I:/llama.cpp/calm3-22b-RP
5
+ parameters:
6
+ weight: 0.5
7
+ merge_method: breadcrumbs
8
+ base_model: I:/llama.cpp/calm3-22b-chat
9
+ dtype: bfloat16
10
+ tokenizer_source: base
11
+ parameters:
12
+ density: 0.9
13
+ gamma: 0.01
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb70432e6272dbff2402064fa1aeb143658d93486ee24812ad703a4ad0f0c7b
3
+ size 4995002336
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68de7a4da179438861557930b77762bcc24cc16201883f8b9da8f3df30f57560
3
+ size 4957808344
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b09df3776d6e229f65e91484bc70d3c122ceb4a01d3e6ba98b01a64b26e406d
3
+ size 4932642288
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8377e3cc28fa9fe2c66502e195509b7b8e69f371765ca74488775a35696c9c3
3
+ size 4831979224
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84004c189747941eea5e4af391e69f97b0011cb6fee07ffcb1163936f982b4ef
3
+ size 4932629880
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32aa27346d553370fd328b2dd6ff58c40375b9026a5d3b8d8ae8a95835238551
3
+ size 4957808360
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d3c01f83047d191e6dc64f99e1a3ea2e93a0bc798ad0f8e352e316cfc247bd
3
+ size 4806813152
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54883b84d45fba8866517578c78b930823bd1fc466a96d43065e51d8351a75c8
3
+ size 4932642296
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74da1da71776ff3fa6e7b5c2be96ba2cfe4c00c64a9a36601a3d399babe25ecb
3
+ size 4831979192
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b1f5a6f265b869c29e82d49d3e06ab2afc379e639540f38a4d052d8c30bd96
3
+ size 905995280
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 45085249536}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.46.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|padding|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
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
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "65000": {
23
+ "content": "[PAD]",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "65001": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "65002": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ }
46
+ },
47
+ "bos_token": "<|endoftext|>",
48
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": true,
50
+ "eos_token": "<|im_end|>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<|padding|>",
53
+ "tokenizer_class": "GPTNeoXTokenizer",
54
+ "unk_token": "<|endoftext|>"
55
+ }