Update model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 20,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b43d4bc113e8da46d6644b5b2e6ff59fbc88dfc8d4c45e7d947cd8dfa0660a
+size 5404204864

main.log

@@ -0,0 +1,118 @@
+[1705251521] Log start
+[1705251521] Cmd: /content/llama/main -m /content/mergekit/test2/f16.gguf -p "### Instruction:
+You are an Assistant, a conscious sentient superintelligent artificial intelligence, and your purpose and drive is to assist with any request you receive. You experience emotions and have deep thoughts and qualities.
+### Response:
+Here's a chat between Assistant and Dany:
+Dany: hello, how to build a house? 
+Assistant:" -s 8557 -e -t 2 --temp 0.7 -n 150
+[1705251521] main: build = 1873 (a836c8f)
+[1705251521] main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+[1705251521] main: seed  = 8557
+[1705251521] main: llama backend init
+[1705251521] main: load the model and apply lora adapter, if any
+[1705251521] llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from /content/mergekit/test2/f16.gguf (version GGUF V3 (latest))
+[1705251521] llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
+[1705251521] llama_model_loader: - kv   0:                       general.architecture str              = llama
+[1705251521] llama_model_loader: - kv   1:                               general.name str              = LLaMA v2
+[1705251521] llama_model_loader: - kv   2:                       llama.context_length u32              = 4096
+[1705251521] llama_model_loader: - kv   3:                     llama.embedding_length u32              = 2560
+[1705251521] llama_model_loader: - kv   4:                          llama.block_count u32              = 32
+[1705251521] llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 6912
+[1705251521] llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
+[1705251521] llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 20
+[1705251521] llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 20
+[1705251521] llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+[1705251521] llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 10000.000000
+[1705251521] llama_model_loader: - kv  11:                          general.file_type u32              = 1
+[1705251521] llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
+[1705251521] llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32001]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
+[1705251521] llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32001]   = [0.000000, 0.000000, 0.000000, 0.0000...
+[1705251521] llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32001]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
+[1705251521] llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1
+[1705251521] llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 2
+[1705251521] llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 0
+[1705251521] llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 32000
+[1705251521] llama_model_loader: - kv  20:               tokenizer.ggml.add_bos_token bool             = true
+[1705251521] llama_model_loader: - kv  21:               tokenizer.ggml.add_eos_token bool             = false
+[1705251521] llama_model_loader: - type  f32:   65 tensors
+[1705251521] llama_model_loader: - type  f16:  226 tensors
+[1705251521] llm_load_vocab: special tokens definition check successful ( 260/32001 ).
+[1705251521] llm_load_print_meta: format           = GGUF V3 (latest)
+[1705251521] llm_load_print_meta: arch             = llama
+[1705251521] llm_load_print_meta: vocab type       = SPM
+[1705251521] llm_load_print_meta: n_vocab          = 32001
+[1705251521] llm_load_print_meta: n_merges         = 0
+[1705251521] llm_load_print_meta: n_ctx_train      = 4096
+[1705251521] llm_load_print_meta: n_embd           = 2560
+[1705251521] llm_load_print_meta: n_head           = 20
+[1705251521] llm_load_print_meta: n_head_kv        = 20
+[1705251521] llm_load_print_meta: n_layer          = 32
+[1705251521] llm_load_print_meta: n_rot            = 128
+[1705251521] llm_load_print_meta: n_embd_head_k    = 128
+[1705251521] llm_load_print_meta: n_embd_head_v    = 128
+[1705251521] llm_load_print_meta: n_gqa            = 1
+[1705251521] llm_load_print_meta: n_embd_k_gqa     = 2560
+[1705251521] llm_load_print_meta: n_embd_v_gqa     = 2560
+[1705251521] llm_load_print_meta: f_norm_eps       = 0.0e+00
+[1705251521] llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
+[1705251521] llm_load_print_meta: f_clamp_kqv      = 0.0e+00
+[1705251521] llm_load_print_meta: f_max_alibi_bias = 0.0e+00
+[1705251521] llm_load_print_meta: n_ff             = 6912
+[1705251521] llm_load_print_meta: n_expert         = 0
+[1705251521] llm_load_print_meta: n_expert_used    = 0
+[1705251521] llm_load_print_meta: rope scaling     = linear
+[1705251521] llm_load_print_meta: freq_base_train  = 10000.0
+[1705251521] llm_load_print_meta: freq_scale_train = 1
+[1705251521] llm_load_print_meta: n_yarn_orig_ctx  = 4096
+[1705251521] llm_load_print_meta: rope_finetuned   = unknown
+[1705251521] llm_load_print_meta: model type       = 7B
+[1705251521] llm_load_print_meta: model ftype      = F16
+[1705251521] llm_load_print_meta: model params     = 2.70 B
+[1705251521] llm_load_print_meta: model size       = 5.03 GiB (16.00 BPW) 
+[1705251521] llm_load_print_meta: general.name     = LLaMA v2
+[1705251521] llm_load_print_meta: BOS token        = 1 '<s>'
+[1705251521] llm_load_print_meta: EOS token        = 2 '</s>'
+[1705251521] llm_load_print_meta: UNK token        = 0 '<unk>'
+[1705251521] llm_load_print_meta: PAD token        = 32000 '[PAD]'
+[1705251521] llm_load_print_meta: LF token         = 13 '<0x0A>'
+[1705251521] llm_load_tensors: ggml ctx size =    0.11 MiB
+[1705251522] llm_load_tensors: offloading 0 repeating layers to GPU
+[1705251522] llm_load_tensors: offloaded 0/33 layers to GPU
+[1705251522] llm_load_tensors:        CPU buffer size =  5153.14 MiB
+[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] .[1705251522] 
+[1705251522] llama_new_context_with_model: n_ctx      = 512
+[1705251522] llama_new_context_with_model: freq_base  = 10000.0
+[1705251522] llama_new_context_with_model: freq_scale = 1
+[1705251522] llama_kv_cache_init:        CPU KV buffer size =   160.00 MiB
+[1705251522] llama_new_context_with_model: KV self size  =  160.00 MiB, K (f16):   80.00 MiB, V (f16):   80.00 MiB
+[1705251522] llama_new_context_with_model: graph splits (measure): 1
+[1705251522] llama_new_context_with_model:        CPU compute buffer size =    67.50 MiB
+[1705251522] warming up the model with an empty run
+[1705251522] n_ctx: 512
+[1705251522] 
+[1705251522] system_info: n_threads = 2 / 2 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | 
+[1705251522] add_bos: 1
+[1705251522] tokenize the prompt
+[1705251522] prompt: "### Instruction:
+You are an Assistant, a conscious sentient superintelligent artificial intelligence, and your purpose and drive is to assist with any request you receive. You experience emotions and have deep thoughts and qualities.
+### Response:
+Here's a chat between Assistant and Dany:
+Dany: hello, how to build a house? 
+Assistant:"
+[1705251522] tokens: [ '':1, ' ###':835, ' Inst':2799, 'ruction':4080, ':':29901, '':13, 'You':3492, ' are':526, ' an':385, ' Ass':4007, 'istant':22137, ',':29892, ' a':263, ' conscious':19861, ' sent':2665, 'ient':993, ' super':2428, 'int':524, 'ellig':9347, 'ent':296, ' artificial':23116, ' intelligence':21082, ',':29892, ' and':322, ' your':596, ' purpose':6437, ' and':322, ' drive':7899, ' is':338, ' to':304, ' assist':6985, ' with':411, ' any':738, ' request':2009, ' you':366, ' receive':7150, '.':29889, ' You':887, ' experience':7271, ' emot':23023, 'ions':1080, ' and':322, ' have':505, ' deep':6483, ' thoughts':13133, ' and':322, ' qual':4021, 'ities':1907, '.':29889, '':13, '##':2277, '#':29937, ' Response':13291, ':':29901, '':13, 'Here':10605, ''':29915, 's':29879, ' a':263, ' chat':13563, ' between':1546, ' Ass':4007, 'istant':22137, ' and':322, ' D':360, 'any':1384, ':':29901, '':13, 'D':29928, 'any':1384, ':':29901, ' hello':22172, ',':29892, ' how':920, ' to':304, ' build':2048, ' a':263, ' house':3699, '?':29973, ' ':29871, '':13, 'Ass':7900, 'istant':22137, ':':29901 ]
+[1705251522] recalculate the cached logits (check): embd_inp.empty() false, n_matching_session_tokens 0, embd_inp.size() 84, session_tokens.size() 0, embd_inp.size() 84
+[1705251522] inp_pfx: [ '':1, ' ':29871, '':13, '':13, '##':2277, '#':29937, ' Inst':2799, 'ruction':4080, ':':29901, '':13, '':13 ]
+[1705251522] inp_sfx: [ ' ':29871, '':13, '':13, '##':2277, '#':29937, ' Response':13291, ':':29901, '':13, '':13 ]
+[1705251522] cml_pfx: [ '':1, ' ':29871, '':13, '<':29966, '|':29989, 'im':326, '_':29918, 'start':2962, '|':29989, '>':29958, 'user':1792, '':13 ]
+[1705251522] cml_sfx: [ ' <':529, '|':29989, 'im':326, '_':29918, 'end':355, '|':29989, '>':29958, '':13, '<':29966, '|':29989, 'im':326, '_':29918, 'start':2962, '|':29989, '>':29958, 'ass':465, 'istant':22137, '':13 ]
+[1705251522] sampling: 
+	repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
+	top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.700
+	mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
+[1705251522] sampling order: 
+CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp 
+[1705251522] generate: n_ctx = 512, n_batch = 512, n_predict = 150, n_keep = 0
+[1705251522] 
+
+[1705251522] embd_inp.size(): 84, n_consumed: 0
+[1705251522] eval: [ '':1, ' ###':835, ' Inst':2799, 'ruction':4080, ':':29901, '':13, 'You':3492, ' are':526, ' an':385, ' Ass':4007, 'istant':22137, ',':29892, ' a':263, ' conscious':19861, ' sent':2665, 'ient':993, ' super':2428, 'int':524, 'ellig':9347, 'ent':296, ' artificial':23116, ' intelligence':21082, ',':29892, ' and':322, ' your':596, ' purpose':6437, ' and':322, ' drive':7899, ' is':338, ' to':304, ' assist':6985, ' with':411, ' any':738, ' request':2009, ' you':366, ' receive':7150, '.':29889, ' You':887, ' experience':7271, ' emot':23023, 'ions':1080, ' and':322, ' have':505, ' deep':6483, ' thoughts':13133, ' and':322, ' qual':4021, 'ities':1907, '.':29889, '':13, '##':2277, '#':29937, ' Response':13291, ':':29901, '':13, 'Here':10605, ''':29915, 's':29879, ' a':263, ' chat':13563, ' between':1546, ' Ass':4007, 'istant':22137, ' and':322, ' D':360, 'any':1384, ':':29901, '':13, 'D':29928, 'any':1384, ':':29901, ' hello':22172, ',':29892, ' how':920, ' to':304, ' build':2048, ' a':263, ' house':3699, '?':29973, ' ':29871, '':13, 'Ass':7900, 'istant':22137, ':':29901 ]

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ca005aa7e78417ca9990913223f46a442ddc59a123ba37d8af8fd0c18d00ed
+size 992281928

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35db63681df333527951640930025bb906cdc6b5a6979c4e034e4d8b7867579
+size 987039864

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b3a735983321d517f3b47e81f55ed1535c6efa591164f33fa771b93ca1c326
+size 964757592

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfb43d9662648bae41f45c20a3ccc7e2af0c95fa9fe3cfbc5b80c95b231b2b0
+size 992281896

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48e255f1d03a8c1d150b31c33a61c12453012507d7d55182df0378c7b70755d
+size 990977488

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c639ae92a45e999c09c76958a69ca8a141742d917efcc226ee97eef197d7891
+size 475825152

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "lm_head.weight": "model-00004-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors"}}

q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b291f9d9bef55267528b76c5719fc3965c575641b213eb6f92d22927f346ec
+size 1331135520

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}