initial revision

README.md

@@ -1,3 +1,57 @@
 ---
 license: cc-by-nc-4.0
+tags:
+- merge
+- conversational
+- multi-task
+pipeline_tag: text-generation
 ---
+
+# Winter Garden 7B - Γ
+
+It was mentioned that we are in the open ai dark winter; so I thought I would make myself a nice winter garden.
+
+## An experiment
+
+This time I did something a bit different.
+
+* Mistral-7B-v0.1
+
+and merged in
+
+* Yarn-Mistral-7b-128k
+* Thespis-Balanced-7b-v1
+* ZySec-7B-v1
+* LemonadeRP-4.5.3
+* Noromaid-7B-0.4-DPO
+* Prima-LelantaclesV6-7b
+* West-Hermes-7B
+* Capricorn-7B-DPO
+* kun-kunoichi-v1-DPO-v2-SLERP-7B
+* Kunoichi-DPO-v2-7B
+* WestLake-7B-v2-laser-truthy-dpo
+* StrangeMerges_6-7B-dare_ties
+* NeuralMarcoro14-7B
+* multi_verse_model
+* Multi-Verse-RP-7B
+* MonarchLake-7B
+* AlphaMonarch-7B
+
+in a consecutive dare ties merge, ordering the merge order by tensor-relative cosine similarity.
+ 
+## Chat Template
+
+Basic Mistral `<s>[INST][/INST]` works pretty well.  It seems smart, but we will see.
+
+## Scores
+
+Metric | Score
+---|---
+
+Average | 
+ARC | 
+HellaSwag | 
+MMLU | 
+TruthfulQA | 
+Winogrande | 
+GSM8K | 

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Mistral-7B-v0.1",
+  "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
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.1"
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392ac60b8e1d879a57b0342b92870beb4086cc6c6b6209984f197a4ea3ad6f7b
+size 262144136

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30bc878a2cb7d06699249127cca10d1166365f884886d707ebb0c8807106731f
+size 1359007112

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8302354c96b500313b18ad65c037e0e916fe62640e27749590b154fcbf9dc1
+size 1577110920

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb98248d0244d9162587a5d9d96fbee2817859acb4271dcc70326bf5c75ee1e
+size 1426132352

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37884c8d72744cccbfe70d4f283b20bdccbf80496037ef514be0603a9a5c3ac1
+size 1359007136

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178d09f370d05423ca156868709f9c21ec5272aaefe740f116ef990ae4d5f6c0
+size 1577110944

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d16b7e8c77671be0b220c34e4942a7e7bd8a047ef89788d9c2911ba5897b01
+size 1426132376

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ac67c569a517d58a5a46101054d16310cb4987f70d995cf4b45774aee60563
+size 1359007136

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d10414c2c0bf65867a5cf1645678381c1527661a6ca517e312eace58fd47613
+size 1577110944

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e2dcc31576c99d90b52aa095a904e20c954e47d061f842d1e6c7947dda08d6
+size 1426132376

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a5c9b60ec39579bde0fac75bf761ae3b4d422fc6c095539db30172747443e5
+size 1134602488

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1.hacklib"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": "<unk>",
+    "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 +1,45 @@
+{
+  "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>",
+  "eos_token": "</s>",
+  "add_generation_prompt": false,
+  "clean_up_tokenization_spaces": false,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}