Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

mergekit_moe_config.yml

@@ -0,0 +1,25 @@
+
+base_model: codellama/CodeLlama-7b-Instruct-hf
+dtype: bfloat16
+gate_mode: hidden
+experts:
+  - source_model: codellama/CodeLlama-7b-Instruct-hf
+    positive_prompts:
+    - "What are the names of all departments that have 'Research' in their name?"
+    - "What is the average salary of employees in each country in the Middle East and Africa region?"
+    - "How many students have an animal or plant allergy?"
+  - source_model: MrezaPRZ/codellama_high_quality_sft
+    positive_prompts:
+    - "SELECT T1.name FROM ACCOUNTS T1 JOIN CHECKING T2 ON T1.custid = T2.custid WHERE date(T2.balance, 'start of month') = date('now', 'start of month') ORDER BY T2.balance ASC LIMIT 1;"
+    - "SELECT MAX(service_datetime) AS latest_booking_date, MIN(service_datetime) AS earliest_booking_date, JULIANDAY(MAX(service_datetime)) - JULIANDAY(MIN(service_datetime)) AS max_time_gap FROM Party_Services;"
+    - "SELECT COUNT(DISTINCT T1.nationality) FROM architect AS T1 JOIN (SELECT architect_id FROM bridge GROUP BY architect_id) AS T2 ON T1.id = T2.architect_id JOIN (SELECT architect_id FROM mill GROUP BY architect_id) AS T3 ON T1.id = T3.architect_id;"
+  - source_model: MrezaPRZ/codellama_high_quality_sft_postgres
+    positive_prompts:
+    - "SELECT state, cname, enr, RANK() OVER (PARTITION BY state ORDER BY enr DESC) as rank FROM college ORDER BY state, rank"
+    - "SELECT T1.title FROM film AS T1 JOIN film_market_estimation AS T2 ON T1.film_id = T2.film_id JOIN market AS T3 ON T2.market_id = T3.market_id WHERE T3.country = 'Japan' AND T1.studio = 'Paramount' ORDER BY T2.high_estimate DESC FETCH FIRST ROW ONLY;"
+    - "SELECT COUNT(DISTINCT T1.country) FROM customers AS T1 JOIN orders AS T2 ON T1.customer_id = T2.customer_id JOIN invoices AS T3 ON T2.order_id = T3.order_id WHERE T2.date_order_placed > NOW() - INTERVAL '1 year' AND T3.invoice_date > NOW() - INTERVAL '1 year';"
+  - source_model: MrezaPRZ/codellama_high_quality_sft_bigquery
+    positive_prompts:
+    - "SELECT T1.Country, COUNT(DISTINCT T1.Artist_ID) AS unique_artists, SUM(T3.Attendance) AS total_attendance FROM artist AS T1 JOIN exhibition AS T2 ON T1.Artist_ID = T2.Artist_ID JOIN exhibition_record AS T3 ON T2.Exhibition_ID = T3.Exhibition_ID WHERE T2.Theme = 'Spring' GROUP BY ROLLUP(T1.Country) HAVING COUNT(DISTINCT T1.Artist_ID) > 1 ORDER BY total_attendance DESC LIMIT 5;"
+    - "SELECT DISTINCT T1.Name AS alias_column, LOWER(T1.Name) AS lname FROM actor T1 WHERE T1.Character LIKE '%Kennedy%'"
+    - "SELECT T1.Service_Type_Code, AVG(CASE WHEN T2.Event_Details = 'Fail' THEN 1 ELSE 0 END) * COUNT(*) AS avg_failed_events FROM Services T1 JOIN Events T2 ON T1.Service_ID = T2.Service_ID WHERE T1.Service_Type_Code <> 'Death Proof' GROUP BY T1.Service_Type_Code"

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb3a1c20877a273b92f3bc81233ea8f8c57d165e4646e2cbd1f7895585f8b6e
+size 9993218016

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d9ec62040c1f6f6b716ce3a16890c610cd86ad63f9d1815956f875affc7d6e
+size 9955338824

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d4f385b105e30760ae97fa00c5132c58cee14b60847bf233a26598cf6a6949
+size 9911290008

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d71c811bc93061156ad93278f4957c90f65127b1da4be21e6c8014c51cabb84
+size 9589502680

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 39449272320}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}