Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+base_model:
+- deepseek-ai/deepseek-math-7b-rl
+- sudhanshu746/deepseek-7b-instruct-matho-finetune
+tags:
+- merge
+- mergekit
+- lazymergekit
+- deepseek-ai/deepseek-math-7b-rl
+- sudhanshu746/deepseek-7b-instruct-matho-finetune
+---
+
+# Deepseek-math-7B-arithmetic-mk-v2
+
+Deepseek-math-7B-arithmetic-mk-v2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [deepseek-ai/deepseek-math-7b-rl](https://huggingface.co/deepseek-ai/deepseek-math-7b-rl)
+* [sudhanshu746/deepseek-7b-instruct-matho-finetune](https://huggingface.co/sudhanshu746/deepseek-7b-instruct-matho-finetune)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: deepseek-ai/deepseek-math-7b-rl
+    parameters:
+      weight: 1
+  - model: sudhanshu746/deepseek-7b-instruct-matho-finetune
+    parameters:
+      weight: 1
+merge_method: task_arithmetic
+base_model: deepseek-ai/deepseek-math-7b-instruct
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "sudhanshu746/Deepseek-math-7B-arithmetic-mk-v2"
+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 +1,29 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-math-7b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}

mergekit_config.yml

@@ -0,0 +1,14 @@
+
+models:
+  - model: deepseek-ai/deepseek-math-7b-rl
+    parameters:
+      weight: 1
+  - model: sudhanshu746/deepseek-7b-instruct-matho-finetune
+    parameters:
+      weight: 1
+merge_method: task_arithmetic
+base_model: deepseek-ai/deepseek-math-7b-instruct
+parameters:
+  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:f082c082d037b2d1f9a5aca3bc5f15e61b5ae3b9cc292cca1a47fd3602f41513
+size 838860928

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0561c9f43dc767be4b91a5d8967b369d56411441bc5f4c13e23c2be1c7307284
+size 929046888

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32f1b642476755b3e5e7d2fc0fc1cfeb10e072cc845ae40db63143c9cc6fa54
+size 989899136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c33d91420d3e4ce80d6f59db4de36cd33d9cb45ae9974cdade0aee76fad16b
+size 943762032

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d892be3b3b67ce91964da0acbf9fb27d0de6f3b5ad7ecf459d0175e4dc257b41
+size 989890840

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76366513e826370d103d27c2d25dc1383af02477f5b66c3caa998edaacd0cdfe
+size 966830592

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8799d5a440a860b6e045dbaa4ea76ec6f211f0810314b56e4b4bd3726b5f36f
+size 966830584

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133f9fcf3c1af8699a438637fb3a68ddae3376bcdbc85170b4697f290efc4e1b
+size 989899144

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0052147bc7bbec12c37dd6b42717f8ebfa3aafc49b5426e53ab0acc87a3bb71f
+size 943762032

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9999a6523c53cc69a19e50fa368a83f8eb5e809d2361d7fffaaa2c6edb149b
+size 989890840

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ac3dcf5079da1988c004911f34e1291fa12e0803ab9a04d531005cdb6e7779
+size 966830592

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f936925786720b6f9c8f878c6ff0e247acf3e66c9bac3e61a52f95b1360b79f
+size 966830576

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38624bae7974c4c9b6dbf0c5157a3f050ae580fa4b31598eaaa2e47b5c0cad45
+size 989899128

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487787ffe00d004187889669febbb596966a89c2b3c2463ff7e723843f5e35c8
+size 943762008

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488b1ba9d6f79dcaa1e6b5acf89d443e169b4010eb922cf0a45e033b49cc0e0e
+size 404767760

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "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 +1,16 @@
+{
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}