tolgadev commited on
Commit
09bb1f0
1 Parent(s): 5a8b272

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - Trendyol/Trendyol-LLM-7b-chat-v1.0
8
+ - Trendyol/Trendyol-LLM-7b-chat-v0.1
9
+ ---
10
+
11
+ # TrendyolMixLLM_v1.1
12
+
13
+ TrendyolMixLLM_v1.1 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [Trendyol/Trendyol-LLM-7b-chat-v1.0](https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-v1.0)
15
+ * [Trendyol/Trendyol-LLM-7b-chat-v0.1](https://huggingface.co/Trendyol/Trendyol-LLM-7b-chat-v0.1)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: Trendyol/Trendyol-LLM-7b-chat-v1.0
23
+ layer_range: [0, 32]
24
+ - sources:
25
+ - model: Trendyol/Trendyol-LLM-7b-chat-v0.1
26
+ layer_range: [24, 32]
27
+ merge_method: passthrough
28
+ dtype: bfloat16
29
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Trendyol/Trendyol-LLM-7b-chat-v1.0",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 44312
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: Trendyol/Trendyol-LLM-7b-chat-v1.0
5
+ layer_range: [0, 32]
6
+ - sources:
7
+ - model: Trendyol/Trendyol-LLM-7b-chat-v0.1
8
+ layer_range: [24, 32]
9
+ merge_method: passthrough
10
+ dtype: bfloat16
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d931464ecb1b183a5f8c7597d750b411a4105e215df1aec3a147a68533b73164
3
+ size 1946227344
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fa7f80e5573df756005d5450f1cc178b7f9ede85d10c0ef7f94aedcdd19518
3
+ size 1979781432
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7957d1bf4c9d2b51fe75b388adc760af5e9e880855d61bbb922c0034a226b8
3
+ size 1990446952
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4d5011b5d822172d450cede072d034a65aed396de7b4106282f68229da3051
3
+ size 1946243984
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b68b57e0d0ff41399a690885d9062a9e9638ab89f137713aeaf91d7766a2f19
3
+ size 1979798064
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58886accefe46d808ec8996a9c3ed0371763962d574dca6ff205d1b9a57363c5
3
+ size 1979781464
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e8e3cc214d0df7c6bb78dd242bf0c17ebe3eee22d5ee61f44a723ddd68648d
3
+ size 1946243984
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb96584e2c6f06a4a94014ea70459081508ec6575d0a5d30932c1fa81799641c
3
+ size 1992381448
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f689c9f31550e4e22ed8ec32701b3375bd59f156814d654ff170b82bd8865b
3
+ size 1981346088
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f546ea03a790d4e728dc5ef79cf9261a4c3615d0f645a0cbe6c35e80c849a260
3
+ size 180371936
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.embed_tokens.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00010.safetensors", "lm_head.weight": "model-00009-of-00010.safetensors", "model.norm.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f2e58f6adbcc203ed4c87b87ed6308abb35e3f854d371c71bd798c9097c724
3
+ size 712489
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }