PowerServe
/

DeepSeek-R1-Distill-Llama-8B-PowerServe-QNN29-8G3

GGUF

conversational

Model card Files Files and versions

xet

Community

llmmlman commited on Feb 5

Commit

435077c

verified ·

1 Parent(s): e8558a4

Update qnn/config.json

Browse files

Files changed (1) hide show

qnn/config.json +8 -8

qnn/config.json CHANGED Viewed

@@ -23,7 +23,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
-      "model_path": "llama3_1_8b_0.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -37,7 +37,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
-      "model_path": "llama3_1_8b_1.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -51,7 +51,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
-      "model_path": "llama3_1_8b_2.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -65,7 +65,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
-      "model_path": "llama3_1_8b_3.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -79,7 +79,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
-      "model_path": "llama3_1_8b_0.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -93,7 +93,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
-      "model_path": "llama3_1_8b_1.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -107,7 +107,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
-      "model_path": "llama3_1_8b_2.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
@@ -121,7 +121,7 @@
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
-      "model_path": "llama3_1_8b_3.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",

       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
+      "model_path": "deepseek_r1_distill_llama_8b_0.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
+      "model_path": "deepseek_r1_distill_llama_8b_1.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
+      "model_path": "deepseek_r1_distill_llama_8b_2.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_1",
+      "model_path": "deepseek_r1_distill_llama_8b_3.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
+      "model_path": "deepseek_r1_distill_llama_8b_0.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
+      "model_path": "deepseek_r1_distill_llama_8b_1.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
+      "model_path": "deepseek_r1_distill_llama_8b_2.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",
       "cache_size": 3968,
       "context_size": 4096,
       "graph_name": "batch_128",
+      "model_path": "deepseek_r1_distill_llama_8b_3.bin",
       "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
       "kv_size": 1,
       "x_name": "x",