first commit

README.md

@@ -1,3 +1,57 @@
----
-license: apache-2.0
----
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: apache-2.0
+---
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* calme-2.4-rys-78b
+* homer-78b (sft on calme-2.4-rys-78b)
+
+
+### How to use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "newsbang/Homer-calme-2.4-78b-mix"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+messages = [
+    {"role": "system", "content": "You are a very helpful assistant."},
+    {"role": "user", "content": "Hello"}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "calme-2.4-rys-78b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+models:
+  - model: homer-78b
+    parameters:
+      weight: 0.5
+  - model: calme-2.4-rys-78b
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: bfloat16

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b584f34c927d367873718e728376d586828613971c15eef20a67e1158647abcd
+size 4969152856

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fb2bcd14756a1221910a7365463bd6866fbfa2baa2c8729d2d50a765721f3e
+size 4980864400

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebf7f52605f8c5eadb412a2b26d0320290f6184e0d56d77a3d52f23ae204e58
+size 4764874368

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40222ff9f8b5ff1e12ab5b2937719e6cf092cabe2ad110250f5dad39bb763e34
+size 4781670352

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf62323d5341ac9a60db713367105eeb85319165b0ad28431ae5718fc8fe664
+size 4781670368

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48267ad5b407048f72de7e716af71d74b44e827675a6d8d304444b6d6f225a8e
+size 4980864408

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8231af95875bd97c6800c06845b80668a7f30d51abf7d9f7cfa6ec6accfeca6
+size 4764874368

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8591f896b219e5d938eb17a3f89e7e5fd8d93ad30b35cc59f64311feb81a4e
+size 4781670352

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f053765ee52b0ad218cf29567df34f1f2d926a79e661473d06cd1f8248b5824
+size 4781670368

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e395ddf8d29779cfc32afc51e99c8490a948a88258ed4eb191d8414e98d122
+size 4980864408

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ea21500476e9b0c063e6514520c55955c0e8f10d79e34677091e1e75a87424
+size 4764874368

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd10fce966e28615f942f6be16f1d34af9572628ee0af202e1db54a935d73bb
+size 4781670352

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0376f938ced531e58d6b1c6922577b8e4a8d4fa3e90584883fa7ce93a2730b6
+size 4781670368

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45bfe00bfadaf44fd0cd7a3a7b7ff5076af2c2c8cb400183d6b612ea42cd836
+size 4980864408

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c30902e046d4008af80248b7b1b8ad45da9e16d832d05bf49b84e3f4b83d71
+size 4764874368

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d4aefa73e4e8834721958068389709b8bb0265d4be6f3dc6a1efd692e0709e
+size 4781670352

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245221d07303b6ab09fcf387c6fdd2e91c0f2ea05f7d7ec0f1b1d1ee91f3266f
+size 4781670368

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f396087dca3c70cc1f7f5b292e6ee4bad1e70fefe7c4a4cf248bb72b56cb573c
+size 4980864408

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c355c4f731d466ebc4fc1341a801843851ea552ecf47553dd45aee41f8ffc0
+size 4764874368

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562014d648d617aa7753b7a0b20199351f981d37f619caa61ff56aef97ac4fa5
+size 4781670352

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da38578481c9f2c566c885520b9c4f57b4f079ca9bb0c79af97aa4d465fc782b
+size 4781670368

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a099eeecb5199c51bd2a369b0017b416d8c117fd02b1deb3a4e06a5f25c33cd
+size 4980864408

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79540e356a585bd638f782b35c99ab018dec713f65ddb9e3698f163de784adc7
+size 4764874368

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed39dba3a14522933dba756ca5ddb5be9e2db2cb74f499d5e53e833c08c6ac95
+size 4781670352

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17267f4bfa7c127c2afbe866138595a19d4a81edd0863325c0a9eca59903987
+size 4781670368

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12dea5a63e795ffdd809b0bed74308ba9da98c93713aea379e4d5c26b259c89
+size 4980864408

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbea8264b232fb867e7eb3214de1ed8470333203df3c557321de4d8a727709f
+size 4764874368

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6dbe147e73f09f6aa8164b734937701191502ca699f0109fe4977d498e1ab9
+size 4781670352

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5ef71cb69fbdb1370fb992ed93b69bef36323ea87bc8f0352b5d63b7101962
+size 4781670368

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b64af4b767d8ce63bedf52bd565189a06799b15ac9bccb602b9861af5a5e82a
+size 4980864408

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c2c03903bf6f3acdaede87025a821e66720c4e30214de7bffc915fee0b2fc7
+size 4764874368

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3568de3110009a8e43c37e6f52b59535c2c0f081e17818bc74b5e1c892797532
+size 4781670352

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3614c0f31b191b8696fe63574795664ca58b76b2535bb759d703f91c09cab410
+size 1270928624

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 155930927104}, "weight_map": {"lm_head.weight": "model-00001-of-00033.safetensors", "model.embed_tokens.weight": "model-00001-of-00033.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", "model.norm.weight": "model-00033-of-00033.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}