Upload folder using huggingface_hub

README.md

@@ -0,0 +1,80 @@
+---
+base_model:
+- deepseek-ai/deepseek-llm-7b-base
+- deepseek-ai/deepseek-coder-7b-base-v1.5
+tags:
+- merge
+- mergekit
+- lazymergekit
+- deepseek-ai/deepseek-llm-7b-base
+- deepseek-ai/deepseek-coder-7b-base-v1.5
+---
+
+# SeekDeep-CodeLM-7B-Base-Ties
+
+SeekDeep-CodeLM-7B-Base-Ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
+* [deepseek-ai/deepseek-coder-7b-base-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-base-v1.5)
+
+## 🧩 Configuration
+
+```yaml
+models:
+
+  - model: deepseek-ai/deepseek-llm-7b-base
+
+    parameters:
+
+      weight: 1
+
+      density: 1
+
+  - model: deepseek-ai/deepseek-coder-7b-base-v1.5
+
+    parameters:
+
+      weight: 1
+
+      density: 1
+
+merge_method: ties
+
+base_model: deepseek-ai/deepseek-llm-7b-base
+
+parameters:
+
+  weight: 1
+
+  density: 1
+
+  normalize: true
+
+  int8_mask: true
+
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "JoPmt/SeekDeep-CodeLM-7B-Base-Ties"
+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 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 102400
+}

mergekit_config.yml

@@ -0,0 +1,34 @@
+
+models:
+
+  - model: deepseek-ai/deepseek-llm-7b-base
+
+    parameters:
+
+      weight: 1
+
+      density: 1
+
+  - model: deepseek-ai/deepseek-coder-7b-base-v1.5
+
+    parameters:
+
+      weight: 1
+
+      density: 1
+
+merge_method: ties
+
+base_model: deepseek-ai/deepseek-llm-7b-base
+
+parameters:
+
+  weight: 1
+
+  density: 1
+
+  normalize: true
+
+  int8_mask: true
+
+dtype: bfloat16

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0b0c18ccd15a804af585d3c3787cb0bdf4de6613bd3ac0a3f5e87b13861821
+size 838860928

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780700cb7b40a78291060d450c980b25eadbb92b707af91849e1679ec1593d14
+size 929046888

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0e245a15ccc9d755b7d58f7892bb2ed9d55668e8fb4d854b12213aaaf0bc82
+size 989899136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d379bab2d9209f577b480ec700c709f534ed51424d06df2c6c73405e95c15a
+size 943762032

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef960123bcdf72e41c3ebde4ba2a348a0cd8d12c35931b7bdbcbb7bfc4821dcd
+size 989890840

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2560dbea3f30a218b92550ef6076ae57146030384f65c3b18787a17196f951
+size 966830592

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3601b802c917bd6d8d270e84053c6a7e231c77ffb881a16d3d607712fb891fd2
+size 966830584

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6314779068052e717f77b2919ecdc0a30937896131cbaed83ea96acb8d6f510f
+size 989899144

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ae7b2361499391ed2f7419849fb39e7f34916a372c02c66cbdda4bddfc9f5e
+size 943762032

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc2e5475596b352d5336ea79dbfa78f3e25c1afe46b895e5e1c0c8927cee274
+size 989890840

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81df7a17dfc50d21bc9068cffcb6722c5a91e66af623dd5fd8ff01c284784efc
+size 966830592

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536c669e5703f908771b60a3e0f8aadeeb3e903b29d27f2eaff11748f49bb1d7
+size 966830576

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631c2e2c554039992c35e0b6f0da5223f78ce42f009cf7ca21dec6e75d1f32c4
+size 989899128

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b02701ad2373f560cbb6f2e7ce25d85873e73315d6c6bba744eafd33eccff1
+size 943762008

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc276b7758f07589734fea918e477d3dcd3c4b1156c051446a11be7e1d6812db
+size 404767760

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 13820731392}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00002-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,137 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}