rudrashah commited on
Commit
09b0691
1 Parent(s): dfdd421

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
8
+ - OpenPipe/mistral-ft-optimized-1218
9
+ ---
10
+
11
+ # RLM-mini
12
+
13
+ RLM-mini is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [EmbeddedLLM/Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1)
15
+ * [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
23
+ layer_range: [0, 32]
24
+ - model: OpenPipe/mistral-ft-optimized-1218
25
+ layer_range: [0, 32]
26
+ merge_method: slerp
27
+ base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
28
+ parameters:
29
+ t:
30
+ - filter: self_attn
31
+ value: [0, 0.5, 0.3, 0.7, 1]
32
+ - filter: mlp
33
+ value: [1, 0.5, 0.7, 0.3, 0]
34
+ - value: 0.5
35
+ dtype: bfloat16
36
+
37
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EmbeddedLLM/Mistral-7B-Merge-14-v0.1",
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
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
5
+ layer_range: [0, 32]
6
+ - model: OpenPipe/mistral-ft-optimized-1218
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.5
17
+ dtype: bfloat16
18
+
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f846b3e453b27dad4079bf817561c4c77f5079d66b9dc2fad10deafb8661723
3
+ size 1950412280
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8def76e835d86a5edbf3167d1e95c523bac6979e80d670c64fecdb3dad4e5926
3
+ size 1988178496
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a066695fce8b270bccfb973055740bcd5d1c61422c16c6e4e728ac8c26804402
3
+ size 1937846944
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb94a56eee1f1ac79a791d4cbe04aeb0235e3107bd22d041ac460bf55fcc5fdb
3
+ size 1988178488
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32adbe9739ac9a493e2faada275db88ce87483cf432117103b4b290127626682
3
+ size 1937846944
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f71545614e8937722d3fe0e3e8abd2c16d31aa6fa8e2b428877b6fcc36cd7d9
3
+ size 1988178488
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d599a40793fd302dd603d3a4e1db85ab084de84c6249ffdda054af840ab832fa
3
+ size 1937846904
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378df63ad40a2b474277cfafeaadc7a8606b38112501ba694dd5d7ef6abde58a
3
+ size 755009440
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }