Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+base_model:
+- mistralai/Mistral-7B-v0.3
+- mistralai/Mistral-7B-v0.3
+- mistralai/Mistral-7B-v0.3
+tags:
+- merge
+- mergekit
+- lazymergekit
+- mistralai/Mistral-7B-v0.3
+---
+
+# Mistral-11B-v0.3
+
+Mistral-11B-v0.3 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
+* [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
+* [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: mistralai/Mistral-7B-v0.3
+        layer_range: [0, 24]
+  - sources: # add middle layers with residuals scaled to zero
+      - model: mistralai/Mistral-7B-v0.3
+        layer_range: [8, 24]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+  - sources:
+      - model: mistralai/Mistral-7B-v0.3
+        layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Corianas/Mistral-11B-v0.3"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,20 @@
+
+slices:
+  - sources:
+      - model: mistralai/Mistral-7B-v0.3
+        layer_range: [0, 24]
+  - sources: # add middle layers with residuals scaled to zero
+      - model: mistralai/Mistral-7B-v0.3
+        layer_range: [8, 24]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+  - sources:
+      - model: mistralai/Mistral-7B-v0.3
+        layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1353d082a77d2427cf28b5894b42b81237e179c623d6a38db4c9732dbf16e5
+size 973104464

model-00002-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2020652915aaa0e42468ff84206df7638b8a8e7d4371e05598924b165f1bfe11
+size 905995864

model-00003-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4b7788ebbba93faf87550048b118d248011dd0697caafa6e42c8c476875c60
+size 989890728

model-00004-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9d7f9058a291d83f136e4ce067cbcfe8bbfc94b936810221e81053e4af8dfe
+size 998296072

model-00005-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bb5a4bedd95523256f031f3f4d32b3bf3218ccf13be5a9a16693ecd04b9257
+size 981502456

model-00006-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c8e4ee62675b2728e6a9d721cc1df26713aa06531dd57885cebe62c4b01713
+size 922798696

model-00007-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d90258a16ec1ec6401ac4b44440395c87836ce6fdca9c63d27db6621dc86a3e
+size 989890728

model-00008-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3406afc77837dbaf12c080fc1e7a7958318210d46147b725126ce94d2ab9ad85
+size 989890728

model-00009-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d29ba98ab745357ca69ba5506e75d4bd200288c352f0b8a1b15add9573a8037
+size 989890728

model-00010-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964be63f355abb717b279ca9b8b012b62d9de60496e73f45067385630fa024cb
+size 989890728

model-00011-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fab9ed099ce9238b9b24c3a8f164ac20961b8d83ea048052abc66cff5a1e503
+size 956353248

model-00012-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fcb32a9f560982d069f6b243706701328cbef7afa71bd19e9c791c840192af
+size 989890728

model-00013-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99995bb79ef7fbcf0df771194e97c1ffa1a895ac1c7805a01a9254e1eaf1a943
+size 989890728

model-00014-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6ebf3fc66ec8a4d9ce7e528378ece258b0a103f6e2dccad73aed21dca62043
+size 989890728

model-00015-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e004f2589679618a353861af4b8c597d037df6013101cb78acbb6746f79dd4
+size 956344952

model-00016-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91f8b15ec225a176d2f28bf23fd96db56c3eb4765f1bb7853905a0f6742df8a
+size 989890728

model-00017-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c15f6ff8bf6c91713b9b1b99df1c8c1ce3f1f0f93c9ee5f3d6d0384407d852a
+size 998287760

model-00018-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a91454d66d21e3a77291c8478976795c35e685528e4df833f5ebb306644c49
+size 947956208

model-00019-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c250e28b069aa2b90ec022dcb83be5c3daac7846e88a80a7e0cffef10d3686a4
+size 989890704

model-00020-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cf6e2743ef25fe1bd581d7e967e4cea7ebc680d94a2401d7c8d7a1ebaf99c2
+size 989890712

model-00021-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb4a98e3bd5b08aeb591cb8c61e978c3ac1962241473bda5bb2a3cb54c7c80e
+size 989899016

model-00022-of-00022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a11d95b529d2c58becf52508e9b445370e1cc53f67ed35abd1489a3d961344d
+size 956344912

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 21475631104}, "weight_map": {"lm_head.weight": "model-00001-of-00022.safetensors", "model.embed_tokens.weight": "model-00001-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.norm.weight": "model-00022-of-00022.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404