Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- THUDM/chatglm3-6b-32k
+- THUDM/chatglm3-6b-32k
+---
+
+# ChatGLM3-12B-slerp
+
+ChatGLM3-12B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [THUDM/chatglm3-6b-32k](https://huggingface.co/THUDM/chatglm3-6b-32k)
+* [THUDM/chatglm3-6b-32k](https://huggingface.co/THUDM/chatglm3-6b-32k)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: THUDM/chatglm3-6b-32k
+        layer_range: [0, 28]
+      - model: THUDM/chatglm3-6b-32k
+        layer_range: [0, 28]
+merge_method: slerp
+base_model: OpenPipe/mistral-ft-optimized-1218
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Chuanming/ChatGLM3-12B-slerp"
+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": "OpenPipe/mistral-ft-optimized-1218",
+  "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": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: THUDM/chatglm3-6b-32k
+        layer_range: [0, 28]
+      - model: THUDM/chatglm3-6b-32k
+        layer_range: [0, 28]
+merge_method: slerp
+base_model: OpenPipe/mistral-ft-optimized-1218
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf236272ff0e9a94a69e20b22081aac33010ca758ec301e2a311e49b52e13384
+size 1939971952

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1110b31037390f221af7d7dd049082c2a119e8643fbed0ae5bdee7375d86bc5
+size 1968300224

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4dc5c733913d1c5095343f763c3784cc7b0b7eb52b9ca36ec9791d4c221387
+size 1927406976

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79399037765dcc3730b519aa921e9c2817b66dfae7705e98bd1aa09623e7fc46
+size 1815209360

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfe78eb04b804d6221b7c2ea55566b459e0156548468d924c147f9bef8653d8
+size 1968291952

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2955c8e5513b3a6c0548ae2a31a9c8907daa1894145c782d5c9890e1b48db5c3
+size 1927423608

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640393651e1757d2dc79035a2d8119efc0c5e7537e923d92daf3a91979a5be65
+size 940591040

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"transformer.embedding.word_embeddings.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors", "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors", "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors", "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors", "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors", "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors", "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors", "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors", "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors", "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors", "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors", "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors", "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors", "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors", "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors", "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors", "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors", "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors", "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.self_attention.dense.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors", "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors", "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors", "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors", "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.self_attention.dense.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors", "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors", "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors", "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors", "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors", "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors", "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.self_attention.dense.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors", "transformer.encoder.final_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors", "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00007.safetensors", "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00007.safetensors", "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00007.safetensors", "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00007.safetensors", "transformer.output_layer.weight": "model-00007-of-00007.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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}