steinzer-narayan commited on
Commit
ff53b83
1 Parent(s): a6fb3ce

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,53 @@
1
  ---
2
- license: cc-by-nc-4.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - NousResearch/Nous-Hermes-2-SOLAR-10.7B
4
+ - Sao10K/Fimbulvetr-11B-v2
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
  ---
11
+ # FimbulHermes-15B-v0.1
12
+
13
+ This is a merge of two of the best [SOLAR](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) derivatives, created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ The model is stable and expressive, but has not been thoroughly evaluated.
16
+
17
+ ## Merge Details
18
+ ### Merge Method
19
+
20
+ This model was merged using the passthrough merge method.
21
+
22
+ ### Models Merged
23
+
24
+ The following models were included in the merge:
25
+ * [NousResearch/Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B)
26
+ * [Sao10K/Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
27
+
28
+ ### Configuration
29
+
30
+ The following YAML configuration was used to produce this model:
31
+
32
+ ```yaml
33
+
34
+ slices:
35
+ - sources:
36
+ - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
37
+ layer_range: [0, 16]
38
+ - sources:
39
+ - model: "Sao10K/Fimbulvetr-11B-v2"
40
+ layer_range: [8, 24]
41
+ - sources:
42
+ - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
43
+ layer_range: [17, 32]
44
+ - sources:
45
+ - model: "Sao10K/Fimbulvetr-11B-v2"
46
+ layer_range: [25, 40]
47
+ - sources:
48
+ - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
49
+ layer_range: [41, 48]
50
+ merge_method: passthrough
51
+ dtype: float16
52
+
53
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "steinzer-narayan/fimbulhermes-15B-v0.1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
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": 69,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.39.3",
26
+ "use_cache": false,
27
+ "vocab_size": 32002
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
5
+ layer_range: [0, 16]
6
+ - sources:
7
+ - model: "Sao10K/Fimbulvetr-11B-v2"
8
+ layer_range: [8, 24]
9
+ - sources:
10
+ - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
11
+ layer_range: [17, 32]
12
+ - sources:
13
+ - model: "Sao10K/Fimbulvetr-11B-v2"
14
+ layer_range: [25, 40]
15
+ - sources:
16
+ - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
17
+ layer_range: [41, 48]
18
+ merge_method: passthrough
19
+ dtype: float16
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d0847763ffbcaf9336d7a41f1aec114d089a519b652df3e8a2a0ab6b3e871a
3
+ size 9909410568
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0977253cf74bd95e66a988a95223ad4a3af4f6d07815f31aef6b89bdebb1a648
3
+ size 9915751936
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8fef68c7738957a5938d76c2ac501d1afbe43f668ba643b8b5f6c222ecd94f
3
+ size 9926227848
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d54f14c33300200f4c331309a691abe7cef390fdb15e143a44b3ff276fcd8e
3
+ size 872466688
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 30623784960}, "weight_map": {"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00004-of-00004.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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
+ "legacy": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": "</s>",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "trust_remote_code": false,
59
+ "unk_token": "<unk>",
60
+ "use_default_system_prompt": true,
61
+ "use_fast": true
62
+ }