Upload folder using huggingface_hub

README.md

@@ -0,0 +1,41 @@
+---
+library_name: transformers
+tags:
+- flow-merge
+- merge
+
+---
+# biomistral_ties
+
+This model is the result of merge of the following models made with flow-merge:
+
+- Base model:
+	- mistralai/Mistral-7B-Instruct-v0.1
+- Models:
+	- BioMistral/BioMistral-Safetensors
+
+
+## flow-merge config
+
+The following configuration was used to merge the models:
+
+```yaml
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+models:
+- path_or_id: mistralai/Mistral-7B-Instruct-v0.1
+  weight: 0.5
+- path_or_id: BioMistral/BioMistral-Safetensors
+  weight: 0.5
+method: ties-merging
+method_global_parameters:
+  scaling_coefficient: 0.7
+  normalize: true
+  top_k: 0.7
+directory_settings:
+  cache_dir: null
+  local_dir: ./models
+  output_dir: ./biomistral_ties
+hf_hub_settings:
+  trust_remote_code: false
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "./biomistral_ties/biomistral_ties",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "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",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

merge_config.yaml

@@ -0,0 +1,74 @@
+!!python/object:flow_merge.lib.merge_config.ValidatedInputData
+__dict__:
+  base_model: mistralai/Mistral-7B-Instruct-v0.1
+  device: null
+  directory_settings: !!python/object:flow_merge.lib.merge_settings.DirectorySettings
+    __dict__:
+      cache_dir: null
+      local_dir: ./models
+      output_dir: ./biomistral_ties
+    __pydantic_extra__: null
+    __pydantic_fields_set__: !!set
+      cache_dir: null
+      local_dir: null
+      output_dir: null
+    __pydantic_private__: null
+  hf_hub_settings: !!python/object:flow_merge.lib.merge_settings.HfHubSettings
+    __dict__:
+      token:
+      trust_remote_code: false
+    __pydantic_extra__: null
+    __pydantic_fields_set__: !!set
+      token: null
+      trust_remote_code: null
+    __pydantic_private__: null
+  method: !!python/object/apply:flow_merge.lib.constants.MergeMethodIdentifier
+  - ties-merging
+  method_global_parameters: !!python/object:flow_merge.lib.merge_settings.MethodGlobalParameters
+    __dict__:
+      normalize: true
+      p: null
+      scaling_coefficient: 0.7
+      t: null
+      top_k: 0.7
+    __pydantic_extra__: null
+    __pydantic_fields_set__: !!set
+      normalize: null
+      scaling_coefficient: null
+      top_k: null
+    __pydantic_private__: null
+  models:
+  - !!python/object:flow_merge.lib.merge_settings.RawModelDict
+    __dict__:
+      path_or_id: mistralai/Mistral-7B-Instruct-v0.1
+      weight: 0.5
+    __pydantic_extra__: null
+    __pydantic_fields_set__: !!set
+      path_or_id: null
+      weight: null
+    __pydantic_private__: null
+  - !!python/object:flow_merge.lib.merge_settings.RawModelDict
+    __dict__:
+      path_or_id: BioMistral/BioMistral-Safetensors
+      weight: 0.5
+    __pydantic_extra__: null
+    __pydantic_fields_set__: !!set
+      path_or_id: null
+      weight: null
+    __pydantic_private__: null
+  tokenizer_settings: !!python/object:flow_merge.lib.merge_settings.TokenizerSettings
+    __dict__:
+      interpolation_method: linear
+      mode: base
+    __pydantic_extra__: null
+    __pydantic_fields_set__: !!set {}
+    __pydantic_private__: null
+__pydantic_extra__: null
+__pydantic_fields_set__: !!set
+  base_model: null
+  directory_settings: null
+  hf_hub_settings: null
+  method: null
+  method_global_parameters: null
+  models: null
+__pydantic_private__: null

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01eb1dc7a921a587bf5d410268a3c2c3249190ab137bd0185ddbf9abb5a1a5b
+size 2007251976

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c846de3936586a1aada6858d8ac9b5fdab3e3663f32f16a04312392fa3e600
+size 2114199616

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e6c23b4cae3db888e15e4a6624cd5dcf6dcff18ee120f2950c77126b5961be
+size 2113931320

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc014d5107a9e32b5ded1a2870b2bc2896e4f1901bbb03b6a31a32ff6bf13311
+size 2113931288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8678a65134fc05df371e9d1e162786d6a78a39595ee1e029bcb4889dcfb668a
+size 2113931288

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad2932de1f2dc797157dfdef73156633a4c21a59eb420b2feac84fb7da80b8f
+size 2113931312

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87136812401766d498584130b1df84cc08b191fb7b86465f01c263e7c820f8b9
+size 1906321192

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_shards": 7, "flow-ai-merger_version": "0.1.0"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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
+}