Model upload

README.md

@@ -0,0 +1,82 @@
+---
+base_model:
+- 152334H/miqu-1-70b-sf
+license: unknown
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- merge
+- frankenmerge
+- 95b
+---
+# BigWeave v28 96b
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/65a6db055c58475cf9e6def1/4CbbAN-X7ZWj702JrcCGH.png" width=600>
+
+The BigWeave models aim to experimentally identify merge settings for increasing model performance. The version number merely tracks various attempts and is not a quality indicator. Only results demonstrating good performance are retained and shared.
+
+# Prompting Format
+Chatml, Mistral, Vicuna.
+
+# Merge process
+This is a self-merge of 152334H/miqu-1-70b-sf. The slices use a uniform size and only overlap with the adjacent sizes by one layer. See [this discussion](https://huggingface.co/llmixer/BigWeave-v16-103b/discussions/2).
+
+Merge configuration:
+```
+slices:
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [0,12]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [10,16]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [14,20]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [18,24]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [22,28]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [26,32]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [30,36]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [34,40]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [38,44]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [42,48]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [46,52]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [50,56]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [54,60]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [58,64]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [62,68]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [66,72]
+  - sources:
+    - model: 152334H/miqu-1-70b-sf
+      layer_range: [70,80]
+merge_method: passthrough
+dtype: float16
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "llmixer/BigWeave-v28-96b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32764,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 112,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c499e777a03e065edae80c245f33f15d0fa62a7d7c6308082f6727161cb7951
+size 9550600160

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e050c03e56063f55710c65de28f4e897a5c030906015f1946585764b0847c1
+size 9965868688

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1e29046628df82f3136c2aaddd0b289e649e17b699557ef6c54beeadffb737
+size 9630258400

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1155f215e72c0529628f4427bf7062436d51da7ce6625b4492f94cbce4684db
+size 9932314760

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18219dbd686ddf4bd8365be30ef3c8348da26ea11f19c78a3c49ac7681f861e6
+size 9697466720

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3acbf7fdd9cb380bdd094eccae5f09828dc024aeac834c0225efb7a606350a7
+size 9630290696

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e851fb96a6a67f572ad69033ab62612bc43236960f49e0ce4f88631f7e70af80
+size 9932249464

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec3e67ebc15cff9af2039fea412d60a0532b55bfb4dec85bdcfb4180ee41b63
+size 9663945056

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e739407e9ff19105f7b01e1896a8d5747bcc6caebcca97ac996bbc2439c1abb3
+size 9663845360

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8fb9cf53a1069f55dfb6266f56bfa59229e94aa43b481372ee35cf11d0876c
+size 9630291400

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d683931629bcac2938fef7783e1b6a52254e69c797a0aafc821117418177c77
+size 9630325096

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58a1c1500c72e5710ae6b4610d465078a636b4d53773a4c6bff11867b91047c
+size 9663879768

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6441dd859552d45d134dc685440a0ef98bd39409a06c1d1896bd7ee95536d43
+size 9663878360

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f925a0e1a57cff37e51344d66eb690e715758474954dff4104a7f4633cba90f8
+size 9932264552

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499ff877e042ad229226de93b436506c89579ec9464db4dbe8d4de60c8d4de12
+size 9630308592

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5571658d10e6c4facf3c3be722ebf421e2436dca6efcb5ba4857cb23e1b4040c
+size 9831650864

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f32422981302e0cbb511ba88e805e8996d2a427dd9db596113073e86f6eee4b
+size 9630357400

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c0b6bff6be076627e676b0eb0c3c64f5928e01f5897d6d67497e4e689a39af
+size 9965803464

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e986acb61868c0a727cb432ec99f8c63059a943daaab88654f99f15f7409e9b
+size 9798129952

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5645576244aa9cde0b82f77a943b49b2e15f936455efdbfc80d9d6333a198b
+size 7671566648

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.52.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.56.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.61.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.59.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.58.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.66.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.64.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.63.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.69.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.67.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.65.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.74.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.73.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.71.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.70.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.78.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.76.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.81.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.80.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.79.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.77.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.86.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.85.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.83.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.84.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.82.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.91.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.89.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.90.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.88.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.87.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.96.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.94.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.93.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.92.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.98.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.97.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.95.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.103.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.101.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.102.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.100.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.99.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.106.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.105.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.104.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.109.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.108.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00020-of-00020.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.107.input_layernorm.weight": "model-00020-of-00020.safetensors", "lm_head.weight": "model-00020-of-00020.safetensors", "model.norm.weight": "model-00020-of-00020.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.111.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00020-of-00020.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.110.input_layernorm.weight": "model-00020-of-00020.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}