luqmanxyz commited on
Commit
c6ec9aa
1 Parent(s): 22eaadd

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - jeonsworld/CarbonVillain-en-10.7B-v1
6
+ - jeonsworld/CarbonVillain-en-10.7B-v1
7
+ base_model:
8
+ - jeonsworld/CarbonVillain-en-10.7B-v1
9
+ - jeonsworld/CarbonVillain-en-10.7B-v1
10
+ ---
11
+
12
+ # FrankenVillain-7B-v1
13
+
14
+ FrankenVillain-7B-v1 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit
15
+ * [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1)
16
+ * [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1)
17
+
18
+ ## 🧩 Configuration
19
+
20
+ ```yaml
21
+ slices:
22
+ - sources:
23
+ - model: jeonsworld/CarbonVillain-en-10.7B-v1
24
+ layer_range: [0, 24]
25
+ - sources:
26
+ - model: jeonsworld/CarbonVillain-en-10.7B-v1
27
+ layer_range: [8, 32]
28
+ merge_method: passthrough
29
+ dtype: bfloat16
30
+ ```
31
+
32
+ ## 💻 Usage
33
+
34
+ ```python
35
+ !pip install -qU transformers accelerate
36
+
37
+ from transformers import AutoTokenizer
38
+ import transformers
39
+ import torch
40
+
41
+ model = "luqmanxyz/FrankenVillain-7B-v1"
42
+ messages = [{"role": "user", "content": "What are the 3 planets closest to the sun"}]
43
+
44
+ tokenizer = AutoTokenizer.from_pretrained(model)
45
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
46
+ pipeline = transformers.pipeline(
47
+ "text-generation",
48
+ model=model,
49
+ torch_dtype=torch.float16,
50
+ device_map="auto",
51
+ )
52
+
53
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
54
+ print(outputs[0]["generated_text"])
55
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jeonsworld/CarbonVillain-en-10.7B-v1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 2,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.35.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: jeonsworld/CarbonVillain-en-10.7B-v1
5
+ layer_range: [0, 24]
6
+ - sources:
7
+ - model: jeonsworld/CarbonVillain-en-10.7B-v1
8
+ layer_range: [8, 32]
9
+ merge_method: passthrough
10
+ dtype: bfloat16
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956fec5fdecfe1cb95ec6694508e4c759222cabd200c4c6ccc702b7971bff29f
3
+ size 1996576448
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844dffb067f621acfe980432ccb7a400cdf64c11b59cb28a8651a2973095b3d9
3
+ size 1946243984
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6ec5248693dbeb114e3966ead602816533b7066d6b2cd986e016ac0a620d79
3
+ size 1979781456
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5ad9ec9c66a49f8cbdbdf4d75ae2bd141351f4ac5efa148a46a70c9561650b
3
+ size 1979781456
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f48c7dbbf71c8879765258f29cfaf26914d5d0589794b2bc856bdd34e783044
3
+ size 1996575976
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd6a9f2602d893735ac91b45c9db7ebbafa4f5bd3aaee341fb88ce69834451b
3
+ size 1895911984
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf5c8bb1446cdc29d280181b85b425664b4dfc46678201abb811cfc2c9ea7fa
3
+ size 1979789712
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6bbff1b2a8e6dd8048367a6331917b77e060c8b26e35a1dbd62e1d7996fe52
3
+ size 1979781416
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e8f5e215a94cdbe45e015cad76a416644070224dbac968469c012f5f90f31b
3
+ size 1889603680
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b14ae1519b9996c3217f238ffd809cb27b88a064387bd28fe44dd677b5618a
3
+ size 1979789744
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ef6661c39bf35485a21f7ef0c6c7e880d2f29387ed347eaab025d986600d6a
3
+ size 1839262880
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.38.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.embed_tokens.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": true
41
+ }