Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- deepseek-ai/deepseek-math-7b-rl
+- deepseek-ai/deepseek-math-7b-instruct
+base_model:
+- deepseek-ai/deepseek-math-7b-rl
+- deepseek-ai/deepseek-math-7b-instruct
+---
+
+# ganeet-V1
+
+ganeet-V1 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)
+* [deepseek-ai/deepseek-math-7b-instruct](https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [0, 30]
+      - model: deepseek-ai/deepseek-math-7b-instruct
+        layer_range: [0, 30]
+merge_method: slerp
+base_model: deepseek-ai/deepseek-math-7b-rl
+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: 0.4
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "snigdhachandan/ganeet-V1"
+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-rl",
+  "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,
+  "model_type": "llama",
+  "moe_intermediate_size": 11008,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [0, 30]
+      - model: deepseek-ai/deepseek-math-7b-instruct
+        layer_range: [0, 30]
+merge_method: slerp
+base_model: deepseek-ai/deepseek-math-7b-rl
+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: 0.4
+dtype: bfloat16

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62f156e7b7f128e65805fb97314e2c0ef5d8d9e5bea97fd780b7acc759d3663
+size 838860928

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a0450e685120d01ff3ffad36416b808c051f1aa4bb20cfaa4fa8331ec5aca4
+size 929046888

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b0562a09339eaa39c50a70b32c4e72a065cca89320d084b333b5d53983e0a3
+size 989899136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d565004f9eb88fe0157523ea7c4165674edc0eda569fa304e7280e7b90c7de9c
+size 943762032

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8040876fb338bd06a0817f8d948c06849084ec5aed0f5f9dc5e85dd2d3eaaff2
+size 989890840

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366ec41ecf0a52119d88d215f2c961132fc387fbed293c532055adabbc2f887f
+size 966830592

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a09b70a9f91b2f635400d3ff281e37fd556314ec98ef3894c39a4b0ba4f59fa
+size 966830584

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a386321d099d701818ad42c57b381e8c09d5cba339c4343b08e37874f4538dc8
+size 989899144

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c11034051f2effbe91c12b26243fc597be30680f73ebf4c0beb725a19178e4
+size 943762032

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56be7ddbd1a23d3b432512bf6a6c44765c01b8cabb2f1f3f22dc0e7e08bd739b
+size 989890840

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa499f2db7eaa34fc79e45facad06f3cbf6f5c82a080e137ec18d02c6e97c0f
+size 966830592

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7193b73ba1c089ffb351e6c457388b126660e237c6b64e33fa723e3d77a010b6
+size 966830576

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fbc22a915b361075e98715dfc2e89bf3ba2ab48133217ac6f51e72b8f41f49
+size 989899128

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b316507da6e896aa23acb7b6ebadf16cba7f19812e7700046893e48dabb70e3e
+size 943762008

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b6800bbda0ab005176a41325d735515ad7b5c164a0698b9785be32c5c65beb
+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
+}