frost19k commited on
Commit
e19035d
1 Parent(s): 7c46614

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - cognitivecomputations/dolphin-2.8-mistral-7b-v02
7
+ - Nondzu/Mistral-7B-Instruct-v0.2-code-ft
8
+ base_model:
9
+ - cognitivecomputations/dolphin-2.8-mistral-7b-v02
10
+ - Nondzu/Mistral-7B-Instruct-v0.2-code-ft
11
+ - cognitivecomputations/dolphin-2.8-mistral-7b-v02
12
+ - Nondzu/Mistral-7B-Instruct-v0.2-code-ft
13
+ - cognitivecomputations/dolphin-2.8-mistral-7b-v02
14
+ ---
15
+
16
+ # dolphin-2.8-mistral-11b-v02-code-ft
17
+
18
+ dolphin-2.8-mistral-11b-v02-code-ft is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
19
+ * [cognitivecomputations/dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)
20
+ * [Nondzu/Mistral-7B-Instruct-v0.2-code-ft](https://huggingface.co/Nondzu/Mistral-7B-Instruct-v0.2-code-ft)
21
+ * [cognitivecomputations/dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)
22
+ * [Nondzu/Mistral-7B-Instruct-v0.2-code-ft](https://huggingface.co/Nondzu/Mistral-7B-Instruct-v0.2-code-ft)
23
+ * [cognitivecomputations/dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)
24
+
25
+ ## 🧩 Configuration
26
+
27
+ ```yaml
28
+ slices:
29
+ - sources:
30
+ - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
31
+ layer_range: [0, 8]
32
+ - sources:
33
+ - model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
34
+ layer_range: [4, 14]
35
+ - sources:
36
+ - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
37
+ layer_range: [10, 20]
38
+ - sources:
39
+ - model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
40
+ layer_range: [16, 26]
41
+ - sources:
42
+ - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
43
+ layer_range: [22, 32]
44
+ merge_method: passthrough
45
+ base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
46
+ dtype: float16
47
+ ```
48
+
49
+ ## 💻 Usage
50
+
51
+ ```python
52
+ !pip install -qU transformers accelerate
53
+
54
+ from transformers import AutoTokenizer
55
+ import transformers
56
+ import torch
57
+
58
+ model = "frost19k/dolphin-2.8-mistral-11b-v02-code-ft"
59
+ messages = [{"role": "user", "content": "What is a large language model?"}]
60
+
61
+ tokenizer = AutoTokenizer.from_pretrained(model)
62
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
63
+ pipeline = transformers.pipeline(
64
+ "text-generation",
65
+ model=model,
66
+ torch_dtype=torch.float16,
67
+ device_map="auto",
68
+ )
69
+
70
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
71
+ print(outputs[0]["generated_text"])
72
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/dolphin-2.8-mistral-7b-v02",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
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": 48,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.40.2",
24
+ "use_cache": false,
25
+ "vocab_size": 32002
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
5
+ layer_range: [0, 8]
6
+ - sources:
7
+ - model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
8
+ layer_range: [4, 14]
9
+ - sources:
10
+ - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
11
+ layer_range: [10, 20]
12
+ - sources:
13
+ - model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
14
+ layer_range: [16, 26]
15
+ - sources:
16
+ - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
17
+ layer_range: [22, 32]
18
+ merge_method: passthrough
19
+ base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
20
+ dtype: float16
model-00001-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f813ad1a3e36af50262c55e983625407d3467ded3a5f48448d20f6f76559bc
3
+ size 960554312
model-00002-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9007fdcb230c5d651f23692cee3593a8487f16dffab73b91a8b52f6bb29ffd3
3
+ size 905995856
model-00003-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d71a3d7c771aeda26435632fa73b50fc7dd92422dc5ec3c99f768fd0610cfd91
3
+ size 989890704
model-00004-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796db9eb59e178211c7438cdf64dd9b56f9e7174c59c0a86ff042080543ee02e
3
+ size 998296048
model-00005-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604eec0f7922359fad8b29371dc110fa63abb4b3166306564935b52d3371eaf1
3
+ size 981502432
model-00006-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200060e5798ce8e75ee9885ac40d8f5f387d3f2ec343fbd10185c71c30d639e3
3
+ size 922798672
model-00007-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b087ea73681c6095e887618f5c1733ee2850859dea276ac95ea34146f65d42
3
+ size 989890712
model-00008-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37746e88908f6b093b3e05cc12ec28921acdb67bd5355a32f9925f8f01381643
3
+ size 989890712
model-00009-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7454da7fa373259b5427d7ea5d8726a1c2bbcca8a0dffba1b8241a8dddd602ba
3
+ size 989890712
model-00010-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82299cb2bef6f6381e9b2432a1ae62337c2ecbebf40bf834e62b6aae8fa57e6
3
+ size 956344912
model-00011-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58161c0afba6cb7629218c6db0b8d43a70d959c785681efe6958e1cb849dc07f
3
+ size 989899008
model-00012-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49eacb6b84145e6cef82ae742705bcdddddf510f75f6af4f0481a55f49e7a8d1
3
+ size 989890712
model-00013-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bacd73657379060275fa96d3beab2819cbf50895cacb4a90117b51ed210163
3
+ size 989890712
model-00014-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b22e6e40610ee3d810f2c3887026b2dfc3139d4c028ef69fefd4ec5458b1f4
3
+ size 989890712
model-00015-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ae847bb13cc9144edb2d097098dac4b506accad86236edb481c88c9ce70c43
3
+ size 956344928
model-00016-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2998b7660693510cc38729852227539096c9694f7b61627146b04b285c56f6
3
+ size 989890712
model-00017-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c8092530b801ad3422f393dd5862603c2fe1b1746ee15e1ccf02a8c3d7371a
3
+ size 998287720
model-00018-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d2b42b79df1ac32d0b433f69196065bf621b137190677131e188bc7382b54d
3
+ size 981501960
model-00019-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df6e7756cbc7ce07cac5444243a9d596c83151422c49914591bcea3f0446792
3
+ size 989890688
model-00020-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e597d071ee8e6ee051849cbd038b9f5fcf528993e1b4f5afe27257170e5d0a61
3
+ size 998296024
model-00021-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758a1c9d8d643555547c858ee8475bb8a88eefa7b0c656f70bca882564bd6598
3
+ size 981502432
model-00022-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c56777fcd7224619c2180c406a4101e4a56dafdef14700daedbb019ffd19a72
3
+ size 922790344
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21463080960}, "weight_map": {"lm_head.weight": "model-00001-of-00022.safetensors", "model.embed_tokens.weight": "model-00001-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.norm.weight": "model-00022-of-00022.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": "<|im_end|>",
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ }
46
+ },
47
+ "bos_token": "<s>",
48
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "<|im_end|>",
51
+ "legacy": true,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "</s>",
54
+ "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": false,
59
+ "use_fast": true
60
+ }