Upload folder using huggingface_hub

README.md

@@ -3,15 +3,15 @@ tags:
 - merge
 - mergekit
 - lazymergekit
-- abacaj/phi-2-super
+- unsloth/gemma-2b
 base_model:
-- abacaj/phi-2-super
+- unsloth/gemma-2b
 ---
 
 # Gemma-2b-rs
 
 Gemma-2b-rs is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [abacaj/phi-2-super](https://huggingface.co/abacaj/phi-2-super)
+* [unsloth/gemma-2b](https://huggingface.co/unsloth/gemma-2b)
 
 ## 🧩 Configuration
 
@@ -19,7 +19,7 @@ Gemma-2b-rs is a merge of the following models using [LazyMergekit](https://cola
 models:
   - model: anakin87/gemma-2b-orpo
     # No parameters necessary for base model
-  - model: abacaj/phi-2-super
+  - model: unsloth/gemma-2b
     parameters:
       density: 0.53
       weight: 0.45

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/gemma-2b-it",
+  "_name_or_path": "anakin87/gemma-2b-orpo",
   "architectures": [
     "GemmaForCausalLM"
   ],
@@ -9,6 +9,7 @@
   "eos_token_id": 1,
   "head_dim": 256,
   "hidden_act": "gelu",
+  "hidden_activation": null,
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 16384,

mergekit_config.yml

@@ -1,13 +1,13 @@
 
 models:
-  - model: unsloth/gemma-2b-it
+  - model: anakin87/gemma-2b-orpo
     # No parameters necessary for base model
   - model: unsloth/gemma-2b
     parameters:
       density: 0.53
       weight: 0.45
 merge_method: dare_ties
-base_model: unsloth/gemma-2b-it
+base_model: anakin87/gemma-2b-orpo
 parameters:
   int8_mask: true
 dtype: bfloat16

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f509e416b44bc88c66703dc2f2b99ff0cfa4219d9ba1f32f6e6dd642f2c0d5
-size 1981895936
+oid sha256:83b35668c4deee8ee07b6453532a97e3b386392f303696007b71fe8de22ef98c
+size 1981883320

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3db066a3b9227965f44ae7c8662b80dc8dba970bc5c2320f3442b02c135077c
-size 1981891672
+oid sha256:2f1983c3d90e21aa4f5b2bc235e9f4d60e0ba7ffa61686cdf391187d7086ee7a
+size 1914782696

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fda4f5258ef36e9e98d01f2af7773fb78e5d843f0d47cdb9df7f035b046fd64
-size 1048576144
+oid sha256:9ffcdafe07795db6d3c83365b7d6d69a23f66ed568e0f84c5d4ae2bcce1e77b6
+size 1115697736

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.norm.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.embed_tokens.weight": "model-00003-of-00003.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 5012344832}, "weight_map": {"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.embed_tokens.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -1,7 +1,7 @@
 {
   "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
+    "<|im_start|>",
+    "<|im_end|>"
   ],
   "bos_token": {
     "content": "<bos>",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
-size 17477929
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
-  "add_bos_token": true,
+  "add_bos_token": false,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
@@ -35,7 +35,7 @@
       "special": true
     },
     "106": {
-      "content": "<start_of_turn>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -43,7 +43,7 @@
       "special": true
     },
     "107": {
-      "content": "<end_of_turn>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -52,11 +52,11 @@
     }
   },
   "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
+    "<|im_start|>",
+    "<|im_end|>"
   ],
   "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% 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'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "legacy": null,