Upload 10 files

README.md

@@ -1,49 +1,54 @@
 ---
 base_model:
-- alpindale/Mistral-7B-v0.2-hf
-- mistralai/Mistral-7B-Instruct-v0.2
-- SanjiWatsuki/Kunoichi-DPO-v2-7B
+- mpasila/Alpacazord-Viking-7B
+- mpasila/Finnish-Viking-Alpaca-V1-7B
 library_name: transformers
 tags:
 - mergekit
 - merge
 
 ---
-# coolmodel1
+# Finnish-Alpacazord-7B
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
+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.
+
 ## Merge Details
 ### Merge Method
 
-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.
+This model was merged using the SLERP merge method.
 
 ### Models Merged
 
 The following models were included in the merge:
-* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
-* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
+* [mpasila/Alpacazord-Viking-7B](https://huggingface.co/mpasila/Alpacazord-Viking-7B)
+* [mpasila/Finnish-Viking-Alpaca-V1-7B](https://huggingface.co/mpasila/Finnish-Viking-Alpaca-V1-7B)
 
 ### Configuration
 
 The following YAML configuration was used to produce this model:
 
 ```yaml
-models:
- - model: alpindale/Mistral-7B-v0.2-hf
- # No parameters necessary for base model
- - model: mistralai/Mistral-7B-Instruct-v0.2
- parameters:
- density: 0.53
- weight: 0.4
- - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
- parameters:
- density: 0.53
- weight: 0.4
-merge_method: dare_ties
-base_model: alpindale/Mistral-7B-v0.2-hf
+slices:
+ - sources:
+ - model: mpasila/Finnish-Viking-Alpaca-V1-7B
+ layer_range: [0, 32]
+ - model: mpasila/Alpacazord-Viking-7B
+ layer_range: [0, 32]
+# or, the equivalent models: syntax:
+# models:
+# - model: psmathur/orca_mini_v3_13b
+# - model: garage-bAInd/Platypus2-13B
+merge_method: slerp
+base_model: mpasila/Finnish-Viking-Alpaca-V1-7B
 parameters:
- int8_mask: true
-dtype: bfloat16
+ t:
+ - filter: self_attn
+ value: [0, 0.5, 0.3, 0.7, 1]
+ - filter: mlp
+ value: [1, 0.5, 0.7, 0.3, 0]
+ - value: 0.5 # fallback for rest of tensors
+dtype: float16
 
 ```

config.json

@@ -1,26 +1,29 @@
 {
- "_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+ "_name_or_path": "mpasila/Finnish-Viking-Alpaca-V1-7B",
  "architectures": [
- "MistralForCausalLM"
+ "LlamaForCausalLM"
  ],
+ "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
- "intermediate_size": 14336,
- "max_position_embeddings": 32768,
- "model_type": "mistral",
+ "intermediate_size": 11008,
+ "max_position_embeddings": 4096,
+ "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
- "num_key_value_heads": 8,
+ "num_key_value_heads": 32,
+ "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
- "rope_theta": 1000000.0,
- "sliding_window": null,
+ "rope_scaling": null,
+ "rope_theta": 10000.0,
  "tie_word_embeddings": false,
- "torch_dtype": "bfloat16",
+ "torch_dtype": "float16",
  "transformers_version": "4.38.2",
+ "untie_embeddings_and_output_weights": true,
  "use_cache": true,
- "vocab_size": 32000
+ "vocab_size": 131072
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419345e3824960b89882c53e4c35e4c4e7ef7a6f532977a7d66a3713ae16452d
-size 3926008768
+oid sha256:9d25dd5f0a66603f6cd23185d877aed0b60ad5014cbdacb72fdd55668ac03f47
+size 3867305600

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b083fbed046c41d61873f5f4595eb9816d061305f7da53259d0f9d36117d4280
-size 3953271680
+oid sha256:790281a0f3335681d360ac5f7cfea7f5dfe5f505802fcca4ed84d1c0d4e7c9d7
+size 3997277336

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3933813da7c174e80f7201e88e952c7758173d7d27ebbef3178563e563c6799
-size 3986858976
+oid sha256:2f412572c361b23988b7dd0bab54d73bbdd8a8b3f4061ba53940959e2e553ac2
+size 3980585088

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb34f1526c7610cf79a761e86476faa37b901467a819a310ef90c458d513912
-size 2617358600
+oid sha256:3cd12bd0458bb93f1c352a4c49290f630475340087750d0129e86c38d8d74a56
+size 3254892432

model.safetensors.index.json

@@ -1 +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"}}
+{"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"}}

special_tokens_map.json

@@ -1,4 +1,26 @@
 {
+ "additional_special_tokens": [
+ "<fim_prefix>",
+ "<fim_middle>",
+ "<fim_suffix>",
+ "<fim_pad>",
+ "<filename>",
+ "<gh_stars>",
+ "<issue_start>",
+ "<issue_comment>",
+ "<issue_closed>",
+ "<jupyter_start>",
+ "<jupyter_text>",
+ "<jupyter_code>",
+ "<jupyter_output>",
+ "<empty_output>",
+ "<commit_before>",
+ "<commit_msg>",
+ "<commit_after>",
+ "<reponame>",
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
  "bos_token": {
  "content": "<s>",
  "lstrip": false,
@@ -13,6 +35,13 @@
  "rstrip": false,
  "single_word": false
  },
+ "pad_token": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
  "unk_token": {
  "content": "<unk>",
  "lstrip": false,

tokenizer_config.json

@@ -1,7 +1,5 @@
 {
- "add_bos_token": true,
- "add_eos_token": false,
- "add_prefix_space": true,
+ "add_prefix_space": false,
  "added_tokens_decoder": {
  "0": {
  "content": "<unk>",
@@ -26,17 +24,204 @@
  "rstrip": false,
  "single_word": false,
  "special": true
+ },
+ "3": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<fim_prefix>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": "<fim_middle>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": "<fim_suffix>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": "<fim_pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": "<filename>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "9": {
+ "content": "<gh_stars>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "10": {
+ "content": "<issue_start>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "11": {
+ "content": "<issue_comment>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "12": {
+ "content": "<issue_closed>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "13": {
+ "content": "<jupyter_start>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "14": {
+ "content": "<jupyter_text>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "15": {
+ "content": "<jupyter_code>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "16": {
+ "content": "<jupyter_output>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "17": {
+ "content": "<empty_output>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "18": {
+ "content": "<commit_before>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "19": {
+ "content": "<commit_msg>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "20": {
+ "content": "<commit_after>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "21": {
+ "content": "<reponame>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "22": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "23": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
  }
  },
+ "additional_special_tokens": [
+ "<fim_prefix>",
+ "<fim_middle>",
+ "<fim_suffix>",
+ "<fim_pad>",
+ "<filename>",
+ "<gh_stars>",
+ "<issue_start>",
+ "<issue_comment>",
+ "<issue_closed>",
+ "<jupyter_start>",
+ "<jupyter_text>",
+ "<jupyter_code>",
+ "<jupyter_output>",
+ "<empty_output>",
+ "<commit_before>",
+ "<commit_msg>",
+ "<commit_after>",
+ "<reponame>",
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
- "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
- "pad_token": null,
- "sp_model_kwargs": {},
- "spaces_between_special_tokens": false,
- "tokenizer_class": "LlamaTokenizer",
- "unk_token": "<unk>",
- "use_default_system_prompt": false
+ "pad_token": "<pad>",
+ "padding_side": "left",
+ "tokenizer_class": "BloomTokenizer",
+ "unk_token": "<unk>"
 }