Upload folder using huggingface_hub

README.md

@@ -19,40 +19,23 @@ SciPhi-Mistral-7B-32k-sliced is a merge of the following models using [LazyMerge
 slices:
   - sources:
       - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [0, 3]
+        layer_range: [0, 12]
   - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [5, 7]
-  - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [10, 10]
+      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+        layer_range: [0, 12]
   - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [17, 23]
-  - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [31, 32]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5
-        layer_range: [0, 1]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5
-        layer_range: [11, 12]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5-Instruct
-        layer_range: [0, 1]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5-Instruct
-        layer_range: [11, 12]
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [0, 12]
+
 merge_method: slerp
-base_model: Locutusque/TinyMistral-248M-v2.5-Instruct
+base_model: teknium/OpenHermes-2.5-Mistral-7B
 parameters:
   t:
   - filter: self_attn
     value: [0, 0.5, 0.3, 0.7, 1]
   - filter: mlp
     value: [1, 0.5, 0.7, 0.3, 0]
-  - value: 0.3
+  - value: 0.5
 dtype: float16
 tokenizer_source: base
 

added_tokens.json

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

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "Locutusque/TinyMistral-248M-v2.5-Instruct",
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
   "architectures": [
     "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
-  "hidden_size": 1024,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 14336,
   "max_position_embeddings": 32768,
   "model_type": "mistral",
   "num_attention_heads": 32,
-  "num_hidden_layers": 16,
+  "num_hidden_layers": 36,
   "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
-  "sliding_window": 32,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.37.2",
-  "use_cache": true,
-  "vocab_size": 32005
+  "use_cache": false,
+  "vocab_size": 32002
 }

mergekit_config.yml

@@ -2,40 +2,23 @@
 slices:
   - sources:
       - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [0, 3]
+        layer_range: [0, 12]
   - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [5, 7]
-  - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [10, 10]
+      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+        layer_range: [0, 12]
   - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [17, 23]
-  - sources:
-      - model: SciPhi/SciPhi-Mistral-7B-32k
-        layer_range: [31, 32]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5
-        layer_range: [0, 1]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5
-        layer_range: [11, 12]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5-Instruct
-        layer_range: [0, 1]
-  - sources:
-      - model: Locutusque/TinyMistral-248M-v2.5-Instruct
-        layer_range: [11, 12]
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [0, 12]
+
 merge_method: slerp
-base_model: Locutusque/TinyMistral-248M-v2.5-Instruct
+base_model: teknium/OpenHermes-2.5-Mistral-7B
 parameters:
   t:
   - filter: self_attn
     value: [0, 0.5, 0.3, 0.7, 1]
   - filter: mlp
     value: [1, 0.5, 0.7, 0.3, 0]
-  - value: 0.3
+  - value: 0.5
 dtype: float16
 tokenizer_source: base
 

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc3c25bccc6c95ddbcfb48264d5c7671a144fe37b78b0c227d41040d57e941b
+size 1979781432

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7dd976fe122617290538ce293a88aa61fce5792f410941410a3e8afbffd6051
+size 1946243944

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a54ad23c20076982c3cbd0233cc70695f5366ab1e6e0ada479055f8a2b5a65
+size 1979773128

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcaeec68e32f0dc5ce5d0fb607dd3fdff898a96ed35218fc4cad059024eeff0
+size 1946235640

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2be50d616761620e7b88252f8cc87fe5b9b7b89937bae7199096bbe5e756a85
+size 1979789736

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb772843404bb698829a1370b83c4563dd079beca3eb7f46a320d1dab7144deb
+size 1946219000

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf922c659a6ef0ccb5a65d3dadf8617c9da49df1ec4db0fd2f561037027b05b0
+size 1946243896

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d72c3500d50fa1eeb173eba39b223bc2310ac8c46530bdf4a19d3aa5d4e0ba8
+size 1950445224

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab050eeae0205c6d5b881dd52a216deecb87a9f97fa32705a4434ec8e970e24
+size 553682288

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.norm.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.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-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-00002-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-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-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00003.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.35.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.embed_tokens.weight": "model-00008-of-00009.safetensors", "lm_head.weight": "model-00008-of-00009.safetensors", "model.norm.weight": "model-00008-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -1,20 +1,13 @@
 {
   "bos_token": {
-    "content": "<|bos|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 32001,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -46,7 +32,7 @@
     },
     {
       "id": 32000,
-      "content": "<|bos|>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -55,34 +41,7 @@
     },
     {
       "id": 32001,
-      "content": "<|endoftext|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32002,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32003,
-      "content": "<|ASSISTANT|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32004,
-      "content": "<|USER|>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -112,7 +71,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<|bos|>",
+          "id": "<s>",
           "type_id": 0
         }
       },
@@ -126,7 +85,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<|bos|>",
+          "id": "<s>",
           "type_id": 0
         }
       },
@@ -138,7 +97,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<|bos|>",
+          "id": "<s>",
           "type_id": 1
         }
       },
@@ -150,13 +109,13 @@
       }
     ],
     "special_tokens": {
-      "<|bos|>": {
-        "id": "<|bos|>",
+      "<s>": {
+        "id": "<s>",
         "ids": [
-          32000
+          1
         ],
         "tokens": [
-          "<|bos|>"
+          "<s>"
         ]
       }
     }

tokenizer_config.json

@@ -27,7 +27,7 @@
       "special": true
     },
     "32000": {
-      "content": "<|bos|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -35,31 +35,7 @@
       "special": true
     },
     "32001": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|ASSISTANT|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|USER|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -68,22 +44,18 @@
     }
   },
   "additional_special_tokens": [],
-  "bos_token": "<|bos|>",
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
-  "max_length": 1536,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
-  "pad_token": "<|endoftext|>",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": true,
+  "use_fast": true
 }