grimjim commited on
Commit
79d37e9
1 Parent(s): 3d73661

Initial release

Browse files
README.md CHANGED
@@ -1,3 +1,50 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - grimjim/zephyr-beta-wizardLM-2-merge-7B
4
+ - core-3/kuno-royale-v2-7b
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+ license: cc-by-nc-4.0
10
  ---
11
+ # zephyr-wizard-kuno-royale-BF16-merge-7B
12
+
13
+ This is an experimental merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). All source model weights are BF16, avoiding issues arising from mixed-precision merges.
14
+
15
+ Although the zephyr beta and WizardLM 2 7B models are touted as SOTA and can generate varied prose compared to base Mistral v0.1, their relatively mediocre benchmarks under GSM-8K suggests only average reasoning capability in one-shot narrative text completion. The kuno-royale-v2 model was selected for merger because of its higher GSM-8K rating.
16
+
17
+ Native prompt format is Alpaca, although at least one of the prior models was fine-tuned to Vicuna.
18
+
19
+ Tested lightly with ChatML instruct prompts, temperature 1, and minP 0.02.
20
+
21
+ ## Merge Details
22
+ ### Merge Method
23
+
24
+ This model was merged using the SLERP merge method.
25
+
26
+ ### Models Merged
27
+
28
+ The following models were included in the merge:
29
+ * [grimjim/zephyr-beta-wizardLM-2-merge-7B](https://huggingface.co/grimjim/zephyr-beta-wizardLM-2-merge-7B)
30
+ * [core-3/kuno-royale-v2-7b](https://huggingface.co/core-3/kuno-royale-v2-7b)
31
+
32
+ ### Configuration
33
+
34
+ The following YAML configuration was used to produce this model:
35
+
36
+ ```yaml
37
+ slices:
38
+ - sources:
39
+ - model: grimjim/zephyr-beta-wizardLM-2-merge-7B
40
+ layer_range: [0,32]
41
+ - model: core-3/kuno-royale-v2-7b
42
+ layer_range: [0,32]
43
+ merge_method: slerp
44
+ base_model: grimjim/zephyr-beta-wizardLM-2-merge-7B
45
+ parameters:
46
+ t:
47
+ - value: 0.5
48
+ dtype: bfloat16
49
+
50
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "grimjim/zephyr-beta-wizardLM-2-merge-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.39.3",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: grimjim/zephyr-beta-wizardLM-2-merge-7B
4
+ layer_range: [0,32]
5
+ - model: core-3/kuno-royale-v2-7b
6
+ layer_range: [0,32]
7
+ merge_method: slerp
8
+ base_model: grimjim/zephyr-beta-wizardLM-2-merge-7B
9
+ parameters:
10
+ t:
11
+ - value: 0.5
12
+ dtype: bfloat16
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33540e01ff5e39e0714bb7031a42400b60a4f1794f1c6ef0af482224f78ea128
3
+ size 5899498992
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f522a0b2a9657588e3214358635577f0a3afe44647168f5e593b339a1323b8
3
+ size 5966640432
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0985b27dc5955c57b62c872d6a673c92f4aa9edf8dfd03ffdc0413fe504bdada
3
+ size 2617358600
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", "lm_head.weight": "model-00002-of-00003.safetensors", "model.norm.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "</s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "truncation_side": "left",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }