Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+base_model:
+- LeroyDyer/Mixtral_AI_CyberBrain_2.0
+- ezelikman/quietstar-8-ahead
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [LeroyDyer/Mixtral_AI_CyberBrain_2.0](https://huggingface.co/LeroyDyer/Mixtral_AI_CyberBrain_2.0)
+* [ezelikman/quietstar-8-ahead](https://huggingface.co/ezelikman/quietstar-8-ahead)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: LeroyDyer/Mixtral_AI_CyberBrain_2.0
+        layer_range: [0, 32]
+      - model: ezelikman/quietstar-8-ahead
+        layer_range: [0, 32]
+# or, the equivalent models: syntax:
+# models:
+#   - model: mistralai/Mistral-7B-Instruct-v0.2
+# LaRGER MODEL MUST BE BASE  or
+#  BASE MODEL MUST BE THE TOKENIZER YOU WISH TO ADOPT 
+# so for models with customized processes they must be the base model
+# If the base model has remote code then this must be collected and added 
+# to the repo after and the config file adusted to allow for automapping to your new repo
+#   - model: yanismiraoui/Yarn-Mistral-7b-128k-sharded
+merge_method: slerp
+base_model: ezelikman/quietstar-8-ahead
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.3, 0.6, 0.3786, 0.6, 0.6]
+    - filter: mlp
+      value: [0.7, 0.4, 0.6, 0.4, 0.7]
+    - value: 0.5 # fallback for rest of tensors
+dtype: float16
+
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|endthought|>": 32000,
+  "<|startthought|>": 32001
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "ezelikman/quietstar-8-ahead",
+  "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,
+  "max_thoughts": 10,
+  "merged_lm_and_talk_heads": false,
+  "merged_lm_and_think_heads": true,
+  "merged_talk_heads": true,
+  "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": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_complex_talk_head": true,
+  "use_complex_think_head": false,
+  "use_concat_talk_head": true,
+  "use_shallow_talk": false,
+  "use_shallow_think": true,
+  "use_weighted_talk_head": true,
+  "vocab_size": 32002
+}

mergekit_config.yml

@@ -0,0 +1,26 @@
+
+slices:
+  - sources:
+      - model: LeroyDyer/Mixtral_AI_CyberBrain_2.0
+        layer_range: [0, 32]
+      - model: ezelikman/quietstar-8-ahead
+        layer_range: [0, 32]
+# or, the equivalent models: syntax:
+# models:
+#   - model: mistralai/Mistral-7B-Instruct-v0.2
+# LaRGER MODEL MUST BE BASE  or
+#  BASE MODEL MUST BE THE TOKENIZER YOU WISH TO ADOPT 
+# so for models with customized processes they must be the base model
+# If the base model has remote code then this must be collected and added 
+# to the repo after and the config file adusted to allow for automapping to your new repo
+#   - model: yanismiraoui/Yarn-Mistral-7b-128k-sharded
+merge_method: slerp
+base_model: ezelikman/quietstar-8-ahead
+parameters:
+  t:
+    - filter: self_attn
+      value: [0.3, 0.6, 0.3786, 0.6, 0.6]
+    - filter: mlp
+      value: [0.7, 0.4, 0.6, 0.4, 0.7]
+    - value: 0.5 # fallback for rest of tensors
+dtype: float16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc41e17f9829f500364eedd1d744ff5b5ed7b1cfd5658ffdd85e3175ad2cb883
+size 1946227296

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7fb33a19931a9d4c268dfe855b822ad6ed9e9d846f7d387304165ac01fce68f
+size 1946227288

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c27739f02510396b0bd773d79cd3d8c4096283195336ba86098df4a83c62e9
+size 1973481432

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ecd6751abbc8163b0e1cb4df0d4c9a6acf3d8e458561347f900e123fb7cfd3
+size 1895895328

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cecdc18ca2cf1726fda929385fb6b61ce86fe4d4b9f32a8b8c3fde4e5611f443
+size 1979798032

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d931074f013f84d0256411252841dd4fed25e8b5b598f65c6a132bb152230a42
+size 1744900176

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4ddd75e1d4d8a5d4c47fdfb0d712fd3bc05374ae3c932124c55cb9ab8fff3b
+size 1889620224

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a71369b0a1b7e8d45beac2f85218c34e9860901a0dc5a2c3303406fe41eb66
+size 1107347944

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.embed_tokens.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.norm.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|endthought|>",
+    "<|startthought|>"
+  ],
+  "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
+  },
+  "pad_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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|endthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|startthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endthought|>",
+    "<|startthought|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}