mpasila commited on
Commit
41255e5
·
verified ·
1 Parent(s): ed7a183

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,54 +1,49 @@
1
  ---
2
  base_model:
3
- - mpasila/Alpacazord-Viking-7B
4
- - mpasila/Finnish-Viking-Alpaca-V1-7B
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
 
10
  ---
11
- # Finnish-Alpacazord-7B
12
 
13
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
 
15
- This is just a test to see if I can improve my models by merging the Finnish data based model with the slightly higher performing English data based model.
16
-
17
  ## Merge Details
18
  ### Merge Method
19
 
20
- This model was merged using the SLERP merge method.
21
 
22
  ### Models Merged
23
 
24
  The following models were included in the merge:
25
- * [mpasila/Alpacazord-Viking-7B](https://huggingface.co/mpasila/Alpacazord-Viking-7B)
26
- * [mpasila/Finnish-Viking-Alpaca-V1-7B](https://huggingface.co/mpasila/Finnish-Viking-Alpaca-V1-7B)
27
 
28
  ### Configuration
29
 
30
  The following YAML configuration was used to produce this model:
31
 
32
  ```yaml
33
- slices:
34
- - sources:
35
- - model: mpasila/Finnish-Viking-Alpaca-V1-7B
36
- layer_range: [0, 32]
37
- - model: mpasila/Alpacazord-Viking-7B
38
- layer_range: [0, 32]
39
- # or, the equivalent models: syntax:
40
- # models:
41
- # - model: psmathur/orca_mini_v3_13b
42
- # - model: garage-bAInd/Platypus2-13B
43
- merge_method: slerp
44
- base_model: mpasila/Finnish-Viking-Alpaca-V1-7B
 
45
  parameters:
46
- t:
47
- - filter: self_attn
48
- value: [0, 0.5, 0.3, 0.7, 1]
49
- - filter: mlp
50
- value: [1, 0.5, 0.7, 0.3, 0]
51
- - value: 0.5 # fallback for rest of tensors
52
- dtype: float16
53
 
54
  ```
 
1
  ---
2
  base_model:
3
+ - alpindale/Mistral-7B-v0.2-hf
4
+ - mistralai/Mistral-7B-Instruct-v0.2
5
+ - SanjiWatsuki/Kunoichi-DPO-v2-7B
6
  library_name: transformers
7
  tags:
8
  - mergekit
9
  - merge
10
 
11
  ---
12
+ # coolmodel1
13
 
14
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
15
 
 
 
16
  ## Merge Details
17
  ### Merge Method
18
 
19
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) as a base.
20
 
21
  ### Models Merged
22
 
23
  The following models were included in the merge:
24
+ * [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
25
+ * [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
26
 
27
  ### Configuration
28
 
29
  The following YAML configuration was used to produce this model:
30
 
31
  ```yaml
32
+ models:
33
+ - model: alpindale/Mistral-7B-v0.2-hf
34
+ # No parameters necessary for base model
35
+ - model: mistralai/Mistral-7B-Instruct-v0.2
36
+ parameters:
37
+ density: 0.53
38
+ weight: 0.4
39
+ - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
40
+ parameters:
41
+ density: 0.53
42
+ weight: 0.4
43
+ merge_method: dare_ties
44
+ base_model: alpindale/Mistral-7B-v0.2-hf
45
  parameters:
46
+ int8_mask: true
47
+ dtype: bfloat16
 
 
 
 
 
48
 
49
  ```
config.json CHANGED
@@ -1,29 +1,26 @@
1
  {
2
- "_name_or_path": "mpasila/Finnish-Viking-Alpaca-V1-7B",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 11008,
14
- "max_position_embeddings": 4096,
15
- "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
- "num_key_value_heads": 32,
19
- "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
  "transformers_version": "4.38.2",
26
- "untie_embeddings_and_output_weights": true,
27
  "use_cache": true,
28
- "vocab_size": 131072
29
  }
 
1
  {
2
+ "_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
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": 1000000.0,
20
+ "sliding_window": null,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
  "transformers_version": "4.38.2",
 
24
  "use_cache": true,
25
+ "vocab_size": 32000
26
  }
mergekit_config.yml CHANGED
@@ -1,20 +1,16 @@
1
- slices:
2
- - sources:
3
- - model: mpasila/Finnish-Viking-Alpaca-V1-7B
4
- layer_range: [0, 32]
5
- - model: mpasila/Alpacazord-Viking-7B
6
- layer_range: [0, 32]
7
- # or, the equivalent models: syntax:
8
- # models:
9
- # - model: psmathur/orca_mini_v3_13b
10
- # - model: garage-bAInd/Platypus2-13B
11
- merge_method: slerp
12
- base_model: mpasila/Finnish-Viking-Alpaca-V1-7B
 
13
  parameters:
14
- t:
15
- - filter: self_attn
16
- value: [0, 0.5, 0.3, 0.7, 1]
17
- - filter: mlp
18
- value: [1, 0.5, 0.7, 0.3, 0]
19
- - value: 0.5 # fallback for rest of tensors
20
- dtype: float16
 
1
+ models:
2
+ - model: alpindale/Mistral-7B-v0.2-hf
3
+ # No parameters necessary for base model
4
+ - model: mistralai/Mistral-7B-Instruct-v0.2
5
+ parameters:
6
+ density: 0.53
7
+ weight: 0.4
8
+ - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
9
+ parameters:
10
+ density: 0.53
11
+ weight: 0.4
12
+ merge_method: dare_ties
13
+ base_model: alpindale/Mistral-7B-v0.2-hf
14
  parameters:
15
+ int8_mask: true
16
+ dtype: bfloat16
 
 
 
 
 
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d25dd5f0a66603f6cd23185d877aed0b60ad5014cbdacb72fdd55668ac03f47
3
- size 3867305600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419345e3824960b89882c53e4c35e4c4e7ef7a6f532977a7d66a3713ae16452d
3
+ size 3926008768
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:790281a0f3335681d360ac5f7cfea7f5dfe5f505802fcca4ed84d1c0d4e7c9d7
3
- size 3997277336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b083fbed046c41d61873f5f4595eb9816d061305f7da53259d0f9d36117d4280
3
+ size 3953271680
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f412572c361b23988b7dd0bab54d73bbdd8a8b3f4061ba53940959e2e553ac2
3
- size 3980585088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3933813da7c174e80f7201e88e952c7758173d7d27ebbef3178563e563c6799
3
+ size 3986858976
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cd12bd0458bb93f1c352a4c49290f630475340087750d0129e86c38d8d74a56
3
- size 3254892432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb34f1526c7610cf79a761e86476faa37b901467a819a310ef90c458d513912
3
+ size 2617358600
model.safetensors.index.json CHANGED
@@ -1 +1 @@
1
- {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 15100026880}, "weight_map": {"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}}
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.embed_tokens.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors"}}
special_tokens_map.json CHANGED
@@ -1,26 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<fim_prefix>",
4
- "<fim_middle>",
5
- "<fim_suffix>",
6
- "<fim_pad>",
7
- "<filename>",
8
- "<gh_stars>",
9
- "<issue_start>",
10
- "<issue_comment>",
11
- "<issue_closed>",
12
- "<jupyter_start>",
13
- "<jupyter_text>",
14
- "<jupyter_code>",
15
- "<jupyter_output>",
16
- "<empty_output>",
17
- "<commit_before>",
18
- "<commit_msg>",
19
- "<commit_after>",
20
- "<reponame>",
21
- "<|im_start|>",
22
- "<|im_end|>"
23
- ],
24
  "bos_token": {
25
  "content": "<s>",
26
  "lstrip": false,
@@ -35,13 +13,6 @@
35
  "rstrip": false,
36
  "single_word": false
37
  },
38
- "pad_token": {
39
- "content": "<pad>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
  "unk_token": {
46
  "content": "<unk>",
47
  "lstrip": false,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
 
 
 
 
 
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
tokenizer.json CHANGED
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 CHANGED
@@ -1,5 +1,7 @@
1
  {
2
- "add_prefix_space": false,
 
 
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<unk>",
@@ -24,204 +26,17 @@
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
- },
28
- "3": {
29
- "content": "<pad>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<fim_prefix>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<fim_middle>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "6": {
53
- "content": "<fim_suffix>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "7": {
61
- "content": "<fim_pad>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "8": {
69
- "content": "<filename>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "9": {
77
- "content": "<gh_stars>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "10": {
85
- "content": "<issue_start>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "11": {
93
- "content": "<issue_comment>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "12": {
101
- "content": "<issue_closed>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "13": {
109
- "content": "<jupyter_start>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "14": {
117
- "content": "<jupyter_text>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "15": {
125
- "content": "<jupyter_code>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "16": {
133
- "content": "<jupyter_output>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "17": {
141
- "content": "<empty_output>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "18": {
149
- "content": "<commit_before>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "19": {
157
- "content": "<commit_msg>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "20": {
165
- "content": "<commit_after>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "21": {
173
- "content": "<reponame>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "22": {
181
- "content": "<|im_start|>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "23": {
189
- "content": "<|im_end|>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": true
195
  }
196
  },
197
- "additional_special_tokens": [
198
- "<fim_prefix>",
199
- "<fim_middle>",
200
- "<fim_suffix>",
201
- "<fim_pad>",
202
- "<filename>",
203
- "<gh_stars>",
204
- "<issue_start>",
205
- "<issue_comment>",
206
- "<issue_closed>",
207
- "<jupyter_start>",
208
- "<jupyter_text>",
209
- "<jupyter_code>",
210
- "<jupyter_output>",
211
- "<empty_output>",
212
- "<commit_before>",
213
- "<commit_msg>",
214
- "<commit_after>",
215
- "<reponame>",
216
- "<|im_start|>",
217
- "<|im_end|>"
218
- ],
219
  "bos_token": "<s>",
220
  "clean_up_tokenization_spaces": false,
221
  "eos_token": "</s>",
 
222
  "model_max_length": 1000000000000000019884624838656,
223
- "pad_token": "<pad>",
224
- "padding_side": "left",
225
- "tokenizer_class": "BloomTokenizer",
226
- "unk_token": "<unk>"
 
 
227
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
 
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  }
30
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
+ "legacy": true,
35
  "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
  }